{"schema": "modelrater-stage-endpoints-flat/1", "source": "GET https://openrouter.ai/api/v1/models/{author}/{slug}/endpoints", "row_count": 1058, "units": {"latency_ms": "latency_last_30m.p50 as returned. Live values are milliseconds (openai/gpt-6.1-terra-pro OpenAI p50 was 2599).", "throughput_tps": "throughput_last_30m.p50 as returned. Treat as tokens per second.", "uptime_*_pct": "uptime_last_5m, uptime_last_30m, and uptime_last_1d as returned. 100 means 100 percent.", "*_per_m": "Per-token price string times 1000000. Blank stays null.", "*_usd": "Raw price for a unit that is not a token (search, image, audio). Not multiplied.", "status": "Integer as returned. 0 was the common value. Do not rename it to online."}, "rows": [{"model_id": "openai/gpt-6.1-terra-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2599, "throughput_tps": 29, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 2.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 6062, "throughput_tps": 88, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 8861.5, "throughput_tps": 154.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 6.0, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": 1.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra-pro:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.5, "completion_per_m": 2.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3489.5, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.78370583994231, "prompt_per_m": 0.5, "completion_per_m": 2.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2052, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1291, "throughput_tps": 59, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 6.0, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": 1.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1223, "throughput_tps": 111, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-terra:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.5, "completion_per_m": 2.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "OpenInference", "tag": "open-inference/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 871, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.0166, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.016499999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1111, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.01181375955524, "prompt_per_m": 0.04, "completion_per_m": 0.5, "input_cache_read_per_m": 0.004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Wafer", "tag": "wafer/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 337, "throughput_tps": 219, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.07, "completion_per_m": 0.5, "input_cache_read_per_m": 0.0069, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Relace", "tag": "relace", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 963, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.07, "completion_per_m": 0.5, "input_cache_read_per_m": 0.008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/flex", "quantization": "fp8", "service_tier": "flex", "status": -5, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 10457, "throughput_tps": 24, "uptime_5m_pct": 100, "uptime_30m_pct": 40, "uptime_1d_pct": 61.22307157748437, "prompt_per_m": 0.0784, "completion_per_m": 0.2352, "input_cache_read_per_m": 0.0023520000000000004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1040000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 348, "throughput_tps": 141, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.08, "completion_per_m": 0.55, "input_cache_read_per_m": 0.008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "InferenceNet", "tag": "inference-net/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1040000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 382, "throughput_tps": 127, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.08, "completion_per_m": 0.55, "input_cache_read_per_m": 0.008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1237.5, "throughput_tps": 46, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.098, "completion_per_m": 0.29400000000000004, "input_cache_read_per_m": 0.0029400000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1823.5, "throughput_tps": 89, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.6, "input_cache_read_per_m": 0.003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Sail Research", "tag": "sail-research/fp4/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1023, "throughput_tps": 65, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.101, "completion_per_m": 0.15, "input_cache_read_per_m": 0.006735, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1179.5, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.101, "completion_per_m": 0.15, "input_cache_read_per_m": 0.006735, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Morph", "tag": "morph/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 667, "throughput_tps": 144, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.103, "completion_per_m": 0.339, "input_cache_read_per_m": 0.004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Decart", "tag": "decart/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 985, "throughput_tps": 125, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72222222222223, "prompt_per_m": 0.129, "completion_per_m": 0.516, "input_cache_read_per_m": 0.0025800000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1042, "throughput_tps": 98, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.135, "completion_per_m": 0.54, "input_cache_read_per_m": 0.0135, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/priority", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2195, "throughput_tps": 46, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14700000000000002, "completion_per_m": 0.441, "input_cache_read_per_m": 0.00441, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Ionstream", "tag": "ionstream", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 891.5, "throughput_tps": 141, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.15, "completion_per_m": 0.51, "input_cache_read_per_m": 0.009500000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Makora", "tag": "makora/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1075.5, "throughput_tps": 164, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86101459346769, "prompt_per_m": 0.15, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1457, "throughput_tps": 127, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.1785, "completion_per_m": 0.714, "input_cache_read_per_m": 0.00357, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 905, "throughput_tps": 170, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.18, "completion_per_m": 0.72, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 2293, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.18, "completion_per_m": 0.72, "input_cache_read_per_m": 0.0036, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 2984, "throughput_tps": 102, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.195, "completion_per_m": 0.78, "input_cache_read_per_m": 0.0039000000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1337, "throughput_tps": 146, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92790194664744, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Fireworks", "tag": "fireworks/spot", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 681, "throughput_tps": 186, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.21, "completion_per_m": 0.84, "input_cache_read_per_m": 0.004200000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Modal", "tag": "modal", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 731, "throughput_tps": 158, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.43302622253721, "prompt_per_m": 0.25, "completion_per_m": 1.0, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1444.5, "throughput_tps": 106, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.28, "completion_per_m": 1.13, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Crusoe", "tag": "crusoe/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 409, "throughput_tps": 142, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.29, "completion_per_m": 1.2, "input_cache_read_per_m": 0.007, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Nebius", "tag": "nebius/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 881, "throughput_tps": 207, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.81780250347705, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 638, "throughput_tps": 162, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72222222222223, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 227, "throughput_tps": 251, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 976, "throughput_tps": 105, "uptime_5m_pct": 40, "uptime_30m_pct": 60, "uptime_1d_pct": 95.37037037037037, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "PrimeIntellect", "tag": "primeintellect", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 730, "throughput_tps": 217, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.85974754558204, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "BaseTen", "tag": "baseten", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 465, "throughput_tps": 217, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.007, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 640.5, "throughput_tps": 173.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92565055762081, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "DeepSeek", "tag": "deepseek", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 921, "throughput_tps": 55, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 706, "throughput_tps": 126, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.33, "completion_per_m": 1.32, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash-1017", "provider_name": "Fireworks", "tag": "fireworks/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 674.5, "throughput_tps": 174, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.009, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-4-argon", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 4255.5, "throughput_tps": 51, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 0.09375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 5.0, "web_search_usd": 0.014, "image_usd": 1e-06, "audio_usd": 1e-06}, {"model_id": "google/gemini-4-argon", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 4408, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.44444444444444, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 0.1875, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 10.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06}, {"model_id": "google/gemini-4-argon", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 5195.5, "throughput_tps": 50, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 0.1875, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 10.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06}, {"model_id": "google/gemini-4-argon", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 5325, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.32352941176471, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 0.1875, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 11.0, "web_search_usd": 0.014, "image_usd": 2.2e-06, "audio_usd": 2.2e-06}, {"model_id": "google/gemini-4-argon", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 3103, "throughput_tps": 19, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.02912621359224, "prompt_per_m": 3.5999999999999996, "completion_per_m": 18.0, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": 0.3375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 18.0, "web_search_usd": 0.014, "image_usd": 3.6e-06, "audio_usd": 3.6e-06}, {"model_id": "google/gemini-4-argon", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2573, "throughput_tps": 42, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.5999999999999996, "completion_per_m": 18.0, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": 0.3375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 18.0, "web_search_usd": 0.014, "image_usd": 3.6e-06, "audio_usd": 3.6e-06}, {"model_id": "google/gemini-4-argon:batch", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 0.1875, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 5.0, "web_search_usd": 0.014, "image_usd": 1e-06, "audio_usd": 1e-06}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1305.5, "throughput_tps": 161, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": 0.19999999999999998, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1347.5, "throughput_tps": 166, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": 0.19999999999999998, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1253, "throughput_tps": 121.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": 0.19999999999999998, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1723.5, "throughput_tps": 164, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": 0.19999999999999998, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2395.5, "throughput_tps": 125, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": 0.19999999999999998, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 978, "throughput_tps": 193, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": 0.22, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 446, "throughput_tps": 179, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": 0.22, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1996, "throughput_tps": 32, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": 0.22, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1749, "throughput_tps": 113.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.15254237288136, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": 0.22, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1093.5, "throughput_tps": 181, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": 0.22, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-haiku-5.5:batch", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.25, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": 0.0625, "input_cache_write_1h_per_m": 0.09999999999999999, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "google/gemini-nano-banana-2.1", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 65536, "max_completion_tokens": 58982, "max_prompt_tokens": null, "latency_ms": 16666, "throughput_tps": 0, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.84532095901005, "prompt_per_m": 1.5, "completion_per_m": 7.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 3e-05}, {"model_id": "mistralai/mistral-large-4-0", "provider_name": "Mistral", "tag": "mistral/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 2979, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.3599999999999999, "completion_per_m": 4.18, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-large-4-0", "provider_name": "Mistral", "tag": "mistral", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1824, "throughput_tps": 58, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72752043596729, "prompt_per_m": 1.3599999999999999, "completion_per_m": 4.18, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-large-4-0", "provider_name": "Mistral", "tag": "mistral/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1171, "throughput_tps": 75, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.496, "completion_per_m": 4.598, "input_cache_read_per_m": 0.154, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 43002.5, "throughput_tps": 116.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 15552.5, "throughput_tps": 26, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 91.83673469387756, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 8561.5, "throughput_tps": 65, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92947813822285, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3219, "throughput_tps": 22, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro", "provider_name": "OpenAI", "tag": "openai/ultrafast", "quantization": "unknown", "service_tier": "ultrafast", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 12.0, "completion_per_m": 60.0, "input_cache_read_per_m": 0.6, "input_cache_write_per_m": 15.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol-pro:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7285, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 53.56643356643357, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 4818.5, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 81.25, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2374, "throughput_tps": 45, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 5044, "throughput_tps": 45, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2905, "throughput_tps": 31, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93011879804332, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2938, "throughput_tps": 27, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.81818181818181, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1264, "throughput_tps": 59, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol", "provider_name": "OpenAI", "tag": "openai/ultrafast", "quantization": "unknown", "service_tier": "ultrafast", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1619, "throughput_tps": 84, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 12.0, "completion_per_m": 60.0, "input_cache_read_per_m": 0.6, "input_cache_write_per_m": 15.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6.1-sol:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3042.5, "throughput_tps": 116, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2063, "throughput_tps": 100, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1439, "throughput_tps": 103, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 975, "throughput_tps": 108, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2204, "throughput_tps": 101, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 549, "throughput_tps": 118, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.90645463049579, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2505, "throughput_tps": 117, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5.5:batch", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": 2.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "qwen/qwen3.8-max-prime", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1281, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92447129909365, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "cohere/command-a-plus", "provider_name": "Cohere", "tag": "cohere", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 192000, "max_completion_tokens": 64000, "max_prompt_tokens": 128000, "latency_ms": 288, "throughput_tps": 143, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.5, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-6-luna-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 18103, "throughput_tps": 37, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.29577464788733, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.25, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": 0.0625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7936, "throughput_tps": 90, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7096.5, "throughput_tps": 96, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna-pro", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 80093, "throughput_tps": 220, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 4533.5, "throughput_tps": 79, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 6291, "throughput_tps": 177, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.0, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": 0.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna-pro:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.25, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": 0.0625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": -2, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7811, "throughput_tps": 25, "uptime_5m_pct": 60, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 96.94444444444444, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.25, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": 0.0625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2278.5, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2075, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.5, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1794, "throughput_tps": 77, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 940, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2120, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.11, "completion_per_m": 0.55, "input_cache_read_per_m": 0.011, "input_cache_write_per_m": 0.1375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 943, "throughput_tps": 126, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.0, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": 0.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-luna:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.25, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": 0.0625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 8852, "throughput_tps": 74, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 6437, "throughput_tps": 32, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol-pro:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7828, "throughput_tps": 118, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.56236323851203, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2533, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2858, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2886, "throughput_tps": 55.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3479, "throughput_tps": 76, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2147, "throughput_tps": 99.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-sol:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 5.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2696.5, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": 8.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1942, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.53416149068323, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": 8.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2913, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": 8.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3533, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": 8.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3495.5, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": 8.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3424, "throughput_tps": 73, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": 8.8, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3402, "throughput_tps": 70, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": 8.8, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": 8.8, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2756.5, "throughput_tps": 88, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": 8.8, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2240.5, "throughput_tps": 94.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": 8.8, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5", "provider_name": "Anthropic", "tag": "anthropic/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1851, "throughput_tps": 184, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 8.0, "completion_per_m": 40.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 10.0, "input_cache_write_1h_per_m": 16.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5.5:batch", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "x-ai/grok-4.7", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1787, "throughput_tps": 84, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.7", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1528, "throughput_tps": 76, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.7", "provider_name": "xAI", "tag": "xai/zdr/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1584, "throughput_tps": 85, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.7", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1663, "throughput_tps": 62, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.7", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 12523, "throughput_tps": 25, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "qwen/qwen3.8-omni-flash", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 3382, "throughput_tps": 55, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.47, "input_cache_read_per_m": 0.016, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "OpenInference", "tag": "open-inference/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 769, "throughput_tps": 76, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0148, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.0048, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Relace", "tag": "relace", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 522, "throughput_tps": 137, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.07, "completion_per_m": 0.5, "input_cache_read_per_m": 0.008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Decart", "tag": "decart/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 730, "throughput_tps": 99, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.05555555555556, "prompt_per_m": 0.09, "completion_per_m": 0.18, "input_cache_read_per_m": 0.018, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Sail Research", "tag": "sail-research/fp4/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 490, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09, "completion_per_m": 0.25, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 491, "throughput_tps": 95, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09, "completion_per_m": 0.25, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Morph", "tag": "morph/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 592.5, "throughput_tps": 145, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.103, "completion_per_m": 0.339, "input_cache_read_per_m": 0.004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1040000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 354, "throughput_tps": 113, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.103, "completion_per_m": 0.6, "input_cache_read_per_m": 0.008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "InferenceNet", "tag": "inference-net/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1040000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 323, "throughput_tps": 149, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.103, "completion_per_m": 0.6, "input_cache_read_per_m": 0.008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 275, "throughput_tps": 96, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.30507296733843, "prompt_per_m": 0.105, "completion_per_m": 0.84, "input_cache_read_per_m": 0.007, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/flex", "quantization": "fp8", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2146, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.78354978354979, "prompt_per_m": 0.112, "completion_per_m": 0.33599999999999997, "input_cache_read_per_m": 0.00336, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "CoreWeave", "tag": "coreweave/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 432, "throughput_tps": 226.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.09722222222223, "prompt_per_m": 0.13, "completion_per_m": 0.65, "input_cache_read_per_m": 0.002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 912, "throughput_tps": 58, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.135, "completion_per_m": 0.54, "input_cache_read_per_m": 0.0135, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 678.5, "throughput_tps": 73, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.42, "input_cache_read_per_m": 0.004200000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1333, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14700000000000002, "completion_per_m": 0.5880000000000001, "input_cache_read_per_m": 0.0029400000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "ModelRun", "tag": "modelrun/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 331, "throughput_tps": 126, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.16999999999999998, "completion_per_m": 0.67, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 2270.5, "throughput_tps": 73.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.38650306748467, "prompt_per_m": 0.18, "completion_per_m": 0.72, "input_cache_read_per_m": 0.0036, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Wafer", "tag": "wafer/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 252, "throughput_tps": 237, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19, "completion_per_m": 0.65, "input_cache_read_per_m": 0.012, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1102, "throughput_tps": 97, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.195, "completion_per_m": 0.78, "input_cache_read_per_m": 0.0039000000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 802, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 94.7839046199702, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/priority", "quantization": "fp8", "service_tier": "priority", "status": -5, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 915, "throughput_tps": 89.5, "uptime_5m_pct": 0, "uptime_30m_pct": 0, "uptime_1d_pct": 82.10450966356478, "prompt_per_m": 0.21, "completion_per_m": 0.63, "input_cache_read_per_m": 0.0063, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Fireworks", "tag": "fireworks/spot", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 478, "throughput_tps": 231, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.21, "completion_per_m": 0.84, "input_cache_read_per_m": 0.004200000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1465.5, "throughput_tps": 110, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.21, "completion_per_m": 0.84, "input_cache_read_per_m": 0.004200000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 548, "throughput_tps": 197, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.22499999999999998, "completion_per_m": 0.8999999999999999, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Makora", "tag": "makora/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 266, "throughput_tps": 106, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86101459346769, "prompt_per_m": 0.26, "completion_per_m": 1.17, "input_cache_read_per_m": 0.0058, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Crusoe", "tag": "crusoe/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 348.5, "throughput_tps": 120, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.29, "completion_per_m": 1.2, "input_cache_read_per_m": 0.007, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 526, "throughput_tps": 53, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Nebius", "tag": "nebius/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048000, "max_completion_tokens": 943200, "max_prompt_tokens": null, "latency_ms": 668, "throughput_tps": 101, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.95543175487465, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "PrimeIntellect", "tag": "primeintellect", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 706.5, "throughput_tps": 169, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Cohere", "tag": "cohere", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 293, "throughput_tps": 222, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.14833215046131, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 834, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "BaseTen", "tag": "baseten/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 158, "throughput_tps": 244, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.007, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 198, "throughput_tps": 219, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1561, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Modal", "tag": "modal", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 313, "throughput_tps": 110, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "BaseTen", "tag": "baseten", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 310, "throughput_tps": 251, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.007, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 286, "throughput_tps": 104, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 739, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 287, "throughput_tps": 186, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93050729673384, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.0075, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 943, "throughput_tps": 128, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.33, "completion_per_m": 1.32, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "Fireworks", "tag": "fireworks/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 280, "throughput_tps": 181, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.009, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash", "provider_name": "BaseTen", "tag": "baseten/fast", "quantization": "unknown", "service_tier": "priority", "status": -5, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 285, "throughput_tps": 182, "uptime_5m_pct": null, "uptime_30m_pct": 0, "uptime_1d_pct": 56.516129032258064, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": 0.014, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash:batch", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.15, "input_cache_read_per_m": 0.004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4.1-flash:batch", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.112, "completion_per_m": 0.33599999999999997, "input_cache_read_per_m": 0.00336, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-6-astra", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2823, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.98224374495561, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 5290, "throughput_tps": 28, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 69.30555555555556, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3230, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-west-2", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7242, "throughput_tps": 38, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 11.0, "completion_per_m": 55.0, "input_cache_read_per_m": 1.1, "input_cache_write_per_m": 13.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 7311, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 94.39252336448598, "prompt_per_m": 11.0, "completion_per_m": 55.0, "input_cache_read_per_m": 1.1, "input_cache_write_per_m": 13.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2576, "throughput_tps": 66, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 20.0, "completion_per_m": 100.0, "input_cache_read_per_m": 2.0, "input_cache_write_per_m": 25.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra", "provider_name": "OpenAI", "tag": "openai/ultrafast", "quantization": "unknown", "service_tier": "ultrafast", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.27536231884058, "prompt_per_m": 60.0, "completion_per_m": 300.0, "input_cache_read_per_m": 6.0, "input_cache_write_per_m": 75.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 44157, "throughput_tps": 216, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2893, "throughput_tps": 13, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 63.970588235294116, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 23133, "throughput_tps": 63, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 11.0, "completion_per_m": 55.0, "input_cache_read_per_m": 1.1, "input_cache_write_per_m": 13.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2953, "throughput_tps": 22.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 20.0, "completion_per_m": 100.0, "input_cache_read_per_m": 2.0, "input_cache_write_per_m": 25.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro", "provider_name": "OpenAI", "tag": "openai/ultrafast", "quantization": "unknown", "service_tier": "ultrafast", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 60.0, "completion_per_m": 300.0, "input_cache_read_per_m": 6.0, "input_cache_write_per_m": 75.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-6-astra-pro:batch", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "qwen/qwen3.8-max-0902", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 2642, "throughput_tps": 34, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.79166666666667, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-max-0902", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1945, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2494, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0208333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": -2, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 18444, "throughput_tps": 38, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 56.2097516099356, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0208333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2464, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.75, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.75, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 7.5e-07}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2537, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.95833333333334, "prompt_per_m": 0.75, "completion_per_m": 3.75, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.75, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 7.5e-07}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2963.5, "throughput_tps": 94, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 91.69649248389405, "prompt_per_m": 0.8250000000000001, "completion_per_m": 4.125, "input_cache_read_per_m": 0.0825, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.125, "web_search_usd": 0.014, "image_usd": 8.25e-07, "audio_usd": 8.25e-07}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 5609, "throughput_tps": 91, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.61431870669746, "prompt_per_m": 1.35, "completion_per_m": 6.75, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": 0.075, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.75, "web_search_usd": 0.014, "image_usd": 1.35e-06, "audio_usd": 1.35e-06}, {"model_id": "google/gemini-3.8-flash", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2051, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.63530269876003, "prompt_per_m": 1.35, "completion_per_m": 6.75, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": 0.075, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.75, "web_search_usd": 0.014, "image_usd": 1.35e-06, "audio_usd": 1.35e-06}, {"model_id": "google/gemini-3.8-flash:batch", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "moonshotai/kimi-k3.1-pro", "provider_name": "Moonshot AI", "tag": "moonshotai/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 3963, "throughput_tps": 33, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3.1-pro", "provider_name": "Moonshot AI", "tag": "moonshotai/highspeed", "quantization": "mxfp4", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 3927, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "SambaNova", "tag": "sambanova", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 4687, "throughput_tps": 54, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.06, "completion_per_m": 0.24, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 5401.5, "throughput_tps": 41.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 95.79188982402448, "prompt_per_m": 0.14250000000000002, "completion_per_m": 0.5700000000000001, "input_cache_read_per_m": 0.01425, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "StreamLake", "tag": "streamlake", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 512000, "max_prompt_tokens": null, "latency_ms": 1965, "throughput_tps": 64.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 92.40506329113924, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1759.5, "throughput_tps": 105, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 1537, "throughput_tps": 63, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.50195160031225, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1212, "throughput_tps": 192, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92313604919293, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "Novita", "tag": "novita/fp16", "quantization": "fp16", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 2026, "throughput_tps": 79, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.82993197278913, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1565.5, "throughput_tps": 105.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 98.34710743801654, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "ModelRun", "tag": "modelrun/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1068, "throughput_tps": 151, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 855, "throughput_tps": 176, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "InferenceNet", "tag": "inference-net/fp4/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 527.5, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 95.73378839590444, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1832, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.69765684051399, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3.1-flash", "provider_name": "Minimax", "tag": "minimax", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 1340, "throughput_tps": 90, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "elorian/glimpse", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 256000, "max_prompt_tokens": null, "latency_ms": 363, "throughput_tps": 209.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 3.0, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "reflection/beam-1.0-501b-a23b", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 526, "throughput_tps": 341, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 1.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "reflection/beam-1.0-501b-a23b", "provider_name": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 647, "throughput_tps": 335.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.0, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "reflection/beam-1.0-501b-a23b", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 549, "throughput_tps": 237.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 1.2, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "reflection/beam-1.0-501b-a23b", "provider_name": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 242, "throughput_tps": 419, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 1.2, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "reflection/beam-1.0-501b-a23b", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 166, "throughput_tps": 160, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 1.2, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inception/mercury-3", "provider_name": "Inception", "tag": "inception", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 776, "throughput_tps": 317, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.35, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moondream/moondream3-preview", "provider_name": "PrimeIntellect", "tag": "primeintellect/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 32000, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": 166, "throughput_tps": 268, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moondream/moondream3.1-9b-a2b", "provider_name": "PrimeIntellect", "tag": "primeintellect/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 32000, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": 168.5, "throughput_tps": 228, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-open", "provider_name": "Makora", "tag": "makora/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 522, "throughput_tps": 166, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-open", "provider_name": "Modal", "tag": "modal", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 317, "throughput_tps": 279, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-open", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 458, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.83319432860718, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-open", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 549.5, "throughput_tps": 117, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-open", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 710.5, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-open", "provider_name": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 465.5, "throughput_tps": 197, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "Darkbloom", "tag": "darkbloom/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1352.5, "throughput_tps": 19, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.98697539797395, "prompt_per_m": 0.06, "completion_per_m": 0.35, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "Crusoe", "tag": "crusoe/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 284, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.78991596638656, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.08, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "Io Net", "tag": "io-net/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 533, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 92.26234340456891, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 275, "throughput_tps": 131, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93050729673384, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 932, "throughput_tps": 21, "uptime_5m_pct": 40, "uptime_30m_pct": 90, "uptime_1d_pct": 92.62357414448668, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "CoreWeave", "tag": "coreweave/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 351, "throughput_tps": 288, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.64985994397759, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "Venice", "tag": "venice/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 322, "throughput_tps": 344.5, "uptime_5m_pct": 60, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 99.02200488997555, "prompt_per_m": 0.19999999999999998, "completion_per_m": 0.5, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 204, "throughput_tps": 308, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 0.5, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-super-vl", "provider_name": "Nebius", "tag": "nebius/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 561, "throughput_tps": 94, "uptime_5m_pct": 60, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 96.46781789638933, "prompt_per_m": 0.3, "completion_per_m": 0.8999999999999999, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "unbiased/pareto-26.10", "provider_name": "Unbiased", "tag": "unbiased", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2302, "throughput_tps": 50.5, "uptime_5m_pct": 100, "uptime_30m_pct": 89.47368421052632, "uptime_1d_pct": 99.74446337308348, "prompt_per_m": 0.7999999999999999, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "unbiased/pareto-26.9", "provider_name": "Unbiased", "tag": "unbiased", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 10381.5, "throughput_tps": 34, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 7.5, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "liquid/lfm-2.5-24b-a2b", "provider_name": "Liquid", "tag": "liquid/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 223, "throughput_tps": 446.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.7, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "scaledown/summarize", "provider_name": "ScaleDown", "tag": "scaledown", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 4000, "max_prompt_tokens": null, "latency_ms": 796, "throughput_tps": 89, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 0.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "scaledown/extract", "provider_name": "ScaleDown", "tag": "scaledown", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 900000, "max_prompt_tokens": null, "latency_ms": 1954, "throughput_tps": 324, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.7080291970803, "prompt_per_m": 0.04, "completion_per_m": 0.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-wonder", "provider_name": "Meta", "tag": "meta", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 3024, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.65181058495823, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.0025}, {"model_id": "stepfun/step-5-preview", "provider_name": "Featherless", "tag": "featherless/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 2989.5, "throughput_tps": 48, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 2.7, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "stepfun/step-5-preview", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1306, "throughput_tps": 142.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.39024390243902, "prompt_per_m": 1.0, "completion_per_m": 2.7, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "stepfun/step-5-preview", "provider_name": "StepFun", "tag": "stepfun/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 64000, "max_prompt_tokens": null, "latency_ms": 3522, "throughput_tps": 103, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 2.7, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inclusionai/ling-3.1-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1060, "throughput_tps": 25, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.22360248447205, "prompt_per_m": 0.075, "completion_per_m": 0.22499999999999998, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inclusionai/ling-3.1-flash", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1066, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.075, "completion_per_m": 0.22499999999999998, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "perceptron/perceptron-mk1.5", "provider_name": "Perceptron", "tag": "perceptron", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 36864, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 442, "throughput_tps": 134, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 1.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "fireworks/ember-1", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 922.5, "throughput_tps": 58.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-prime", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1328.5, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.70717423133236, "prompt_per_m": 2.8, "completion_per_m": 8.8, "input_cache_read_per_m": 0.56, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "aion-labs/aion-3.5-mini", "provider_name": "AionLabs", "tag": "aion-labs", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1426, "throughput_tps": 58, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.7, "completion_per_m": 1.4, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "aion-labs/aion-3.5", "provider_name": "AionLabs", "tag": "aion-labs", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1714, "throughput_tps": 51, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.9176276771005, "prompt_per_m": 3.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.75, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "upstage/solar-mini4", "provider_name": "Upstage", "tag": "upstage/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2196, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "upstage/solar-mini4", "provider_name": "Upstage", "tag": "upstage", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1764, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": 0.005, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-pro-ultraspeed", "provider_name": "Xiaomi", "tag": "xiaomi/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2266, "throughput_tps": 145, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.35, "completion_per_m": 8.7, "input_cache_read_per_m": 0.036, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Io Net", "tag": "io-net/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048320, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1313.5, "throughput_tps": 99, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.16434540389972, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.28, "input_cache_read_per_m": 0.003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Darkbloom", "tag": "darkbloom/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 4051, "throughput_tps": 20, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.36601307189542, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.28, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "GMICloud", "tag": "gmicloud/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 945000, "max_prompt_tokens": null, "latency_ms": 2982, "throughput_tps": 30, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.09154437456324, "prompt_per_m": 0.119, "completion_per_m": 0.238, "input_cache_read_per_m": 0.00255, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Makora", "tag": "makora/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 885, "throughput_tps": 46, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.95833333333334, "prompt_per_m": 0.13, "completion_per_m": 0.28, "input_cache_read_per_m": 0.002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Relace", "tag": "relace/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1044, "throughput_tps": 96, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.13, "completion_per_m": 0.28, "input_cache_read_per_m": 0.003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Cohere", "tag": "cohere", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1134, "throughput_tps": 76, "uptime_5m_pct": 100, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 4654, "throughput_tps": 28, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.0028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1155, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.30555555555556, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.0028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Xiaomi", "tag": "xiaomi/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 3517.5, "throughput_tps": 36, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.0028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-flash", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2562.5, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.51239669421487, "prompt_per_m": 0.175, "completion_per_m": 0.35, "input_cache_read_per_m": 0.00375, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-pro", "provider_name": "GMICloud", "tag": "gmicloud/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 945000, "max_prompt_tokens": null, "latency_ms": 4321, "throughput_tps": 37, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.36974999999999997, "completion_per_m": 0.7394999999999999, "input_cache_read_per_m": 0.0034, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-pro", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1574, "throughput_tps": 21, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.79166666666667, "prompt_per_m": 0.387, "completion_per_m": 0.7829999999999999, "input_cache_read_per_m": 0.00324, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-pro", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 3152, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.435, "completion_per_m": 0.87, "input_cache_read_per_m": 0.0036, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-pro", "provider_name": "Xiaomi", "tag": "xiaomi/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2936.5, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.435, "completion_per_m": 0.87, "input_cache_read_per_m": 0.0036, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.6-pro", "provider_name": "StreamLake", "tag": "streamlake", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2590.5, "throughput_tps": 27, "uptime_5m_pct": null, "uptime_30m_pct": 40, "uptime_1d_pct": 91.21265377855887, "prompt_per_m": 0.522, "completion_per_m": 1.044, "input_cache_read_per_m": 0.00432, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "prism-ml/ternary-bonsai-2-27b", "provider_name": "Darkbloom", "tag": "darkbloom/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 5969.5, "throughput_tps": 30.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.075, "completion_per_m": 0.5, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flashx", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1669, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.37, "completion_per_m": 1.25, "input_cache_read_per_m": 0.09, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inference-net/schematron-v2-turbo", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 1296.5, "throughput_tps": 202, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 94.11764705882352, "prompt_per_m": 0.03, "completion_per_m": 0.15, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inference-net/schematron-v2-turbo", "provider_name": "InferenceNet", "tag": "inference-net/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 1336, "throughput_tps": 204, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 94.44444444444444, "prompt_per_m": 0.03, "completion_per_m": 0.15, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inference-net/schematron-v2-small", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.22999999999999998, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inference-net/schematron-v2-small", "provider_name": "InferenceNet", "tag": "inference-net/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": 242.5, "throughput_tps": 227, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.22999999999999998, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "sakana/fugu-ultra-v2", "provider_name": "Sakana AI", "tag": "sakana", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 4571, "throughput_tps": 8, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 30.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "sakana/fugu-max", "provider_name": "Sakana AI", "tag": "sakana", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 4268.5, "throughput_tps": 70, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "inclusionai/ling-3.0-flash-vl", "provider_name": "DeepInfra", "tag": "deepinfra/fp16", "quantization": "fp16", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 675, "throughput_tps": 34, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.79013641133263, "prompt_per_m": 0.06, "completion_per_m": 0.18, "input_cache_read_per_m": 0.012, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inception/mercury-2.5", "provider_name": "Inception", "tag": "inception", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 260000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 785, "throughput_tps": 214, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 0.15, "input_cache_read_per_m": 0.004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nex-agi/nex-n2.5-mini", "provider_name": "Nex AGI", "tag": "nex-agi/bf16", "quantization": "bf16", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 632, "throughput_tps": 63, "uptime_5m_pct": 60, "uptime_30m_pct": 76.66666666666667, "uptime_1d_pct": 99.09407665505226, "prompt_per_m": 0.024999999999999998, "completion_per_m": 0.09999999999999999, "input_cache_read_per_m": 0.0025, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nex-agi/nex-n2.5-pro", "provider_name": "Nex AGI", "tag": "nex-agi/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1915, "throughput_tps": 53, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.86648865153538, "prompt_per_m": 0.075, "completion_per_m": 0.25, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-1.3-contributor", "provider_name": "Meta", "tag": "meta", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2596, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": 0.002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.0025}, {"model_id": "meta/muse-spark-1.3", "provider_name": "Meta", "tag": "meta", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2122, "throughput_tps": 186, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.0025}, {"model_id": "anthropic/claude-fable-5.1", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 4068.5, "throughput_tps": 62, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5.1", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3380.5, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5.1", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 5908.5, "throughput_tps": 50, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5.1", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 737, "throughput_tps": 54, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "ibm-granite/granite-4.2-8b", "provider_name": "CoreWeave", "tag": "coreweave/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 518, "throughput_tps": 30, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.91438356164383, "prompt_per_m": 0.06, "completion_per_m": 0.15, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "ibm-granite/granite-4.2-8b", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 431, "throughput_tps": 53, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.06, "completion_per_m": 0.25, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "Io Net", "tag": "io-net/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262124, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1352, "throughput_tps": 38, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.86363636363636, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "GMICloud", "tag": "gmicloud/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 4432, "throughput_tps": 23.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 90.625, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 64000, "max_prompt_tokens": null, "latency_ms": 2239.5, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "Cohere", "tag": "cohere", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 3822, "throughput_tps": 38, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.5004995004995, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2627.5, "throughput_tps": 21, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.70951343500363, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 64000, "max_prompt_tokens": null, "latency_ms": 3857, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1838, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.62880475129919, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy4-preview", "provider_name": "Tencent", "tag": "tencent/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 64000, "max_prompt_tokens": null, "latency_ms": 2715, "throughput_tps": 45.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.834, "completion_per_m": 2.501, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-flash", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 2002.5, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.47, "input_cache_read_per_m": 0.016, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-flash", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1181, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.47, "input_cache_read_per_m": 0.016, "input_cache_write_per_m": 0.19999999999999998, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Relace", "tag": "relace", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1371, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.034499999999999996, "completion_per_m": 0.0823, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "OpenInference", "tag": "open-inference/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 591, "throughput_tps": 130, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0363, "completion_per_m": 0.12100000000000001, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Wafer", "tag": "wafer/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 389, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 95.3813855843247, "prompt_per_m": 0.054, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": 0.053, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Darkbloom", "tag": "darkbloom/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3255.5, "throughput_tps": 26, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 91.32867132867133, "prompt_per_m": 0.065, "completion_per_m": 0.18, "input_cache_read_per_m": 0.0325, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1347, "throughput_tps": 52, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.075, "completion_per_m": 0.25, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Sail Research", "tag": "sail-research/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 910, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.71969166082691, "prompt_per_m": 0.07835, "completion_per_m": 0.25, "input_cache_read_per_m": 0.026099999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1326, "throughput_tps": 54.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.5457986373959, "prompt_per_m": 0.07835, "completion_per_m": 0.25, "input_cache_read_per_m": 0.026099999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Near AI", "tag": "near-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1140, "throughput_tps": 22, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.08, "completion_per_m": 0.5, "input_cache_read_per_m": 0.012, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2988.5, "throughput_tps": 33, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.08399999999999999, "completion_per_m": 0.28, "input_cache_read_per_m": 0.016800000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2667, "throughput_tps": 38, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.65277777777779, "prompt_per_m": 0.08850000000000001, "completion_per_m": 0.295, "input_cache_read_per_m": 0.0177, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 542, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.108, "completion_per_m": 0.35, "input_cache_read_per_m": 0.032, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 604, "throughput_tps": 93, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.108, "completion_per_m": 0.35, "input_cache_read_per_m": 0.032, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "CoreWeave", "tag": "coreweave/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 614, "throughput_tps": 114, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.12, "completion_per_m": 0.38, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 953, "throughput_tps": 133, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.12, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "NextBit", "tag": "nextbit/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1186, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72183588317107, "prompt_per_m": 0.125, "completion_per_m": 0.5, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Phala", "tag": "phala/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2933, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.7977369165488, "prompt_per_m": 0.1275, "completion_per_m": 0.425, "input_cache_read_per_m": 0.0255, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 867, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13124999999999998, "completion_per_m": 0.4375, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Makora", "tag": "makora", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 804.5, "throughput_tps": 104, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93045897079277, "prompt_per_m": 0.14, "completion_per_m": 0.47, "input_cache_read_per_m": 0.024, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Mistral", "tag": "mistral", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1390, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.87261146496816, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Cohere", "tag": "cohere", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 682, "throughput_tps": 127, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "PrimeIntellect", "tag": "primeintellect", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 884, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 921600, "max_prompt_tokens": null, "latency_ms": 3026, "throughput_tps": 46, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 91.51624548736463, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Modal", "tag": "modal/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 333, "throughput_tps": 81, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "BaseTen", "tag": "baseten/fp8/us", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 623, "throughput_tps": 70, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Crusoe", "tag": "crusoe/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1092, "throughput_tps": 114, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 3979, "throughput_tps": 50, "uptime_5m_pct": 100, "uptime_30m_pct": 86.20689655172413, "uptime_1d_pct": 90.34229828850856, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1917.5, "throughput_tps": 84, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Friendli", "tag": "friendli", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 588, "throughput_tps": 155, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 2254, "throughput_tps": 27, "uptime_5m_pct": 80, "uptime_30m_pct": 86.20689655172413, "uptime_1d_pct": 93.24424647364515, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 583.5, "throughput_tps": 147, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.16666666666667, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1074.5, "throughput_tps": 106, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.453125, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "BaseTen", "tag": "baseten/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1012, "throughput_tps": 54, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1679.5, "throughput_tps": 91, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93050729673384, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1305, "throughput_tps": 37, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2119.5, "throughput_tps": 37, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Inceptron", "tag": "inceptron/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 554.5, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.79166666666667, "prompt_per_m": 0.16999999999999998, "completion_per_m": 0.6, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Fireworks", "tag": "fireworks/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 779, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.79166666666667, "prompt_per_m": 0.22499999999999998, "completion_per_m": 0.75, "input_cache_read_per_m": 0.045, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3-flash", "provider_name": "Morph", "tag": "morph/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1970, "throughput_tps": 111, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.28099999999999997, "completion_per_m": 0.42300000000000004, "input_cache_read_per_m": 0.056, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-1.2-contributor", "provider_name": "Meta", "tag": "meta", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1983, "throughput_tps": 185.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": 0.002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.0025}, {"model_id": "deepseek/deepseek-v4-flash-vision-exp", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 893, "throughput_tps": 122.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.21559999999999999, "completion_per_m": 0.6468, "input_cache_read_per_m": 0.00686, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-vision-exp", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 1375, "throughput_tps": 106, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.014, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-vision-exp", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1769, "throughput_tps": 147, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy-mt2-1.8b", "provider_name": "Tencent", "tag": "tencent/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 8192, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": 619, "throughput_tps": 167, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.044, "completion_per_m": 0.17700000000000002, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy-mt2-30b-a3b", "provider_name": "Tencent", "tag": "tencent/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 8192, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": 783, "throughput_tps": 41, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.442119944212, "prompt_per_m": 0.074, "completion_per_m": 0.295, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy-mt2-7b", "provider_name": "Tencent", "tag": "tencent/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 8192, "max_completion_tokens": 4096, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.16666666666667, "prompt_per_m": 0.074, "completion_per_m": 0.295, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Wafer", "tag": "wafer/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 392, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0699, "completion_per_m": 1.4, "input_cache_read_per_m": 0.0689, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Relace", "tag": "relace", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1391.5, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0703, "completion_per_m": 4.3843, "input_cache_read_per_m": 0.0703, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 520, "throughput_tps": 106, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.08, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": 0.07600000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 402, "throughput_tps": 120, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.08, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": 0.07600000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1277, "throughput_tps": 59, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 2.0999999999999996, "input_cache_read_per_m": 0.105, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Makora", "tag": "makora/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 496, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.37839937839938, "prompt_per_m": 0.14, "completion_per_m": 4.4, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Wafer", "tag": "wafer/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 325, "throughput_tps": 111, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.179, "completion_per_m": 1.4, "input_cache_read_per_m": 0.17800000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2387, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19, "completion_per_m": 4.4, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "DekaLLM", "tag": "dekallm", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1063, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 2.95, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Sail Research", "tag": "sail-research/us", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 890.5, "throughput_tps": 77, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 2.0, "input_cache_read_per_m": 0.08, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Sail Research", "tag": "sail-research/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 918, "throughput_tps": 102, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 2.0, "input_cache_read_per_m": 0.08, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1135, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.35691318327974, "prompt_per_m": 0.5625, "completion_per_m": 2.5, "input_cache_read_per_m": 0.125, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Tenstorrent", "tag": "tenstorrent/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1044480, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 871, "throughput_tps": 77, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 2.5, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1766.5, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.63, "completion_per_m": 1.9800000000000002, "input_cache_read_per_m": 0.117, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1433, "throughput_tps": 49, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.71153846153847, "prompt_per_m": 0.7, "completion_per_m": 2.2, "input_cache_read_per_m": 0.13, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 6832, "throughput_tps": 22, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.14529914529915, "prompt_per_m": 0.7, "completion_per_m": 2.2, "input_cache_read_per_m": 0.13, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Morph", "tag": "morph/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 819, "throughput_tps": 81, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.63636363636364, "prompt_per_m": 0.811, "completion_per_m": 5.442, "input_cache_read_per_m": 0.151, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2274, "throughput_tps": 43, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.84, "completion_per_m": 2.64, "input_cache_read_per_m": 0.156, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Decart", "tag": "decart/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 798, "throughput_tps": 112, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.84, "completion_per_m": 2.69, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 717, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.9099999999999999, "completion_per_m": 2.8600000000000003, "input_cache_read_per_m": 0.16899999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Fireworks", "tag": "fireworks/spot", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 642, "throughput_tps": 101, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.98, "completion_per_m": 3.08, "input_cache_read_per_m": 0.182, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "PrimeIntellect", "tag": "primeintellect", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1221.5, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.98, "completion_per_m": 3.08, "input_cache_read_per_m": 0.182, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2455.5, "throughput_tps": 46, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.19, "completion_per_m": 3.74, "input_cache_read_per_m": 0.238, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Inceptron", "tag": "inceptron/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1208, "throughput_tps": 98, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 3.5, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "CoreWeave", "tag": "coreweave/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 783, "throughput_tps": 74, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.5819397993311, "prompt_per_m": 1.2, "completion_per_m": 4.0, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Friendli", "tag": "friendli", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 678, "throughput_tps": 94, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.26, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.234, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Mistral", "tag": "mistral/zdr", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1349, "throughput_tps": 111, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 849, "throughput_tps": 54, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.6923076923077, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "BaseTen", "tag": "baseten/fp4/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1625, "throughput_tps": 80, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Mistral", "tag": "mistral/nvfp4", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 734.5, "throughput_tps": 208, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 921600, "max_prompt_tokens": null, "latency_ms": 512, "throughput_tps": 113, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Crusoe", "tag": "crusoe/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 548, "throughput_tps": 134, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92025518341308, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 733, "throughput_tps": 70, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 741.5, "throughput_tps": 85, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 837.5, "throughput_tps": 107, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.91431019708654, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Modal", "tag": "modal", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 263, "throughput_tps": 114, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 2030.5, "throughput_tps": 73, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 4314, "throughput_tps": 34, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 4277, "throughput_tps": 32, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1587, "throughput_tps": 51.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1576, "throughput_tps": 55, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Mistral", "tag": "mistral/nvfp4/eu", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 402, "throughput_tps": 197, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.54, "completion_per_m": 4.84, "input_cache_read_per_m": 0.154, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2257.5, "throughput_tps": 90, "uptime_5m_pct": 100, "uptime_30m_pct": 86.95652173913044, "uptime_1d_pct": 92.55079006772009, "prompt_per_m": 1.68, "completion_per_m": 5.28, "input_cache_read_per_m": 0.312, "input_cache_write_per_m": 2.0999999999999996, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "ModelRun", "tag": "modelrun/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 295, "throughput_tps": 156, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 92.05607476635514, "prompt_per_m": 2.0999999999999996, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Fireworks", "tag": "fireworks/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1341, "throughput_tps": 85, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.10174639331815, "prompt_per_m": 2.0999999999999996, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.39, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "BaseTen", "tag": "baseten/us/fast", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 474, "throughput_tps": 171.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.91666666666666, "prompt_per_m": 2.0999999999999996, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "BaseTen", "tag": "baseten/fast", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 512, "throughput_tps": 149, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.72495446265937, "prompt_per_m": 2.0999999999999996, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.3", "provider_name": "Alibaba", "tag": "alibaba/prime", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1311, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.8, "completion_per_m": 8.8, "input_cache_read_per_m": 0.56, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Darkbloom", "tag": "darkbloom/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1794, "throughput_tps": 30, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 96.51022864019254, "prompt_per_m": 0.035, "completion_per_m": 2.2, "input_cache_read_per_m": 0.0175, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Chutes", "tag": "chutes/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2019, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86091794158554, "prompt_per_m": 0.039, "completion_per_m": 1.25, "input_cache_read_per_m": 0.0039000000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Near AI", "tag": "near-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 606, "throughput_tps": 65, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 1.35, "input_cache_read_per_m": 0.018, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Ionstream", "tag": "ionstream/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 427, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.87250650477016, "prompt_per_m": 0.04, "completion_per_m": 1.95, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Reka", "tag": "reka/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 265, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 2.2, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Modal", "tag": "modal", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 417, "throughput_tps": 155, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 2.3, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Wafer", "tag": "wafer/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 8158, "throughput_tps": 32, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 2.3, "input_cache_read_per_m": 0.039, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "DekaLLM", "tag": "dekallm", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 467, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.04, "completion_per_m": 2.5, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Tenstorrent", "tag": "tenstorrent/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 407.5, "throughput_tps": 45, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.44444444444444, "prompt_per_m": 0.06, "completion_per_m": 0.5, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 508, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 621, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.60377358490567, "prompt_per_m": 0.18, "completion_per_m": 2.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "ModelRun", "tag": "modelrun/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 85, "throughput_tps": 149, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 2.5, "input_cache_read_per_m": 0.09, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 9214, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.23071479122434, "prompt_per_m": 0.19999999999999998, "completion_per_m": 2.5, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 430, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.22499999999999998, "completion_per_m": 1.9800000000000002, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 503, "throughput_tps": 50, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92957746478874, "prompt_per_m": 0.24, "completion_per_m": 2.2, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "CoreWeave", "tag": "coreweave/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 534.5, "throughput_tps": 54, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.39999999999999997, "completion_per_m": 3.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 7002, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.42, "completion_per_m": 3.0, "input_cache_read_per_m": 0.08499999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2305.5, "throughput_tps": 36, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 92.27436823104694, "prompt_per_m": 0.425, "completion_per_m": 2.5500000000000003, "input_cache_read_per_m": 0.08499999999999999, "input_cache_write_per_m": 0.53125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 3070, "throughput_tps": 33, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 823, "throughput_tps": 98.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-27b", "provider_name": "Cerebras", "tag": "cerebras/fp16", "quantization": "fp16", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 369, "throughput_tps": 616.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.9900000000000001, "completion_per_m": 1.49, "input_cache_read_per_m": 0.9900000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 13412, "throughput_tps": 77.5, "uptime_5m_pct": null, "uptime_30m_pct": 0, "uptime_1d_pct": 51.91815856777494, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0208333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1704.5, "throughput_tps": 73, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0208333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3332, "throughput_tps": 99, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.75, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.75, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 7.5e-07}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2138, "throughput_tps": 110, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.75, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.75, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 7.5e-07}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.8250000000000001, "completion_per_m": 4.125, "input_cache_read_per_m": 0.0825, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.125, "web_search_usd": 0.014, "image_usd": 8.25e-07, "audio_usd": 8.25e-07}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1754, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.35, "completion_per_m": 6.75, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": 0.075, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.75, "web_search_usd": 0.014, "image_usd": 1.35e-06, "audio_usd": 1.35e-06}, {"model_id": "google/gemini-3.7-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1765.5, "throughput_tps": 63, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.35, "completion_per_m": 6.75, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": 0.075, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.75, "web_search_usd": 0.014, "image_usd": 1.35e-06, "audio_usd": 1.35e-06}, {"model_id": "bytedance-seed/seed-2-1-turbo", "provider_name": "Seed", "tag": "seed/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 3274, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.85272459499264, "prompt_per_m": 0.5, "completion_per_m": 2.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-2.4t-a95b", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 7317.5, "throughput_tps": 33, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-2.4t-a95b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1713, "throughput_tps": 42, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-2.4t-a95b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1670, "throughput_tps": 42, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-2.4t-a95b", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 742, "throughput_tps": 89, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.60238568588468, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.8-2.4t-a95b", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1010000, "max_completion_tokens": 909000, "max_prompt_tokens": null, "latency_ms": 866, "throughput_tps": 54, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "bytedance-seed/seed-2.0-code", "provider_name": "Seed", "tag": "seed/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 482, "throughput_tps": 62, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 3.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Relace", "tag": "relace/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1128.5, "throughput_tps": 111, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.78962131837307, "prompt_per_m": 0.2542, "completion_per_m": 8.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Wafer", "tag": "wafer/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 480, "throughput_tps": 122, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93050729673384, "prompt_per_m": 0.28500000000000003, "completion_per_m": 4.300000000000001, "input_cache_read_per_m": 0.284, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Ionstream", "tag": "ionstream", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 984, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.37, "completion_per_m": 2.9299999999999997, "input_cache_read_per_m": 0.088, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Sail Research", "tag": "sail-research/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 797, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 0.7999999999999999, "input_cache_read_per_m": 0.065, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 773.5, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 0.7999999999999999, "input_cache_read_per_m": 0.065, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "StreamLake", "tag": "streamlake", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 2575, "throughput_tps": 46, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.23611111111111, "prompt_per_m": 0.66, "completion_per_m": 1.9800000000000002, "input_cache_read_per_m": 0.022, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 2349, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.9900000000000001, "completion_per_m": 2.9699999999999998, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 2929, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.00497512437812, "prompt_per_m": 1.0559999999999998, "completion_per_m": 3.168, "input_cache_read_per_m": 0.035199999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "DekaLLM", "tag": "dekallm", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1360, "throughput_tps": 88, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.87820512820514, "prompt_per_m": 1.08, "completion_per_m": 3.8, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1497, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.91204925241864, "prompt_per_m": 1.122, "completion_per_m": 3.366, "input_cache_read_per_m": 0.1122, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 1104, "throughput_tps": 76, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.8048780487805, "prompt_per_m": 1.3, "completion_per_m": 2.6, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "CoreWeave", "tag": "coreweave/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 779, "throughput_tps": 110, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.2083035075161, "prompt_per_m": 1.31, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.044, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 753.5, "throughput_tps": 47, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 92.66055045871559, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.13199999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1129.5, "throughput_tps": 83.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.13199999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1384, "throughput_tps": 67, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.3975903614458, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.13199999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Nebius", "tag": "nebius/fp8", "quantization": "fp8", "service_tier": null, "status": -5, "context_length": 979000, "max_completion_tokens": 881100, "max_prompt_tokens": null, "latency_ms": 16140, "throughput_tps": 14, "uptime_5m_pct": 100, "uptime_30m_pct": 66.66666666666666, "uptime_1d_pct": 96.01518026565465, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 2065, "throughput_tps": 50, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.79736575481256, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1056, "throughput_tps": 46, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.5575221238938, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.044, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 675.5, "throughput_tps": 122, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.14224446032881, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.13, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 948, "throughput_tps": 44, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.044, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 3364, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.45945945945947, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.044, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1171, "throughput_tps": 43, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.24812030075188, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.044, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "DeepSeek", "tag": "deepseek", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 990, "throughput_tps": 33, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.32, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.044, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 3292, "throughput_tps": 54, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 95.41984732824427, "prompt_per_m": 1.4500000000000002, "completion_per_m": 4.359999999999999, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro-0813", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 941, "throughput_tps": 93, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.6500000000000001, "completion_per_m": 4.95, "input_cache_read_per_m": 0.165, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "x-ai/grok-4.6", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1827.5, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.6", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1843, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.6", "provider_name": "xAI", "tag": "xai/zdr/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.6", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-west-2", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 0.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "x-ai/grok-4.6", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.6", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "liquid/lfm-2.5-2.6b", "provider_name": "Liquid", "tag": "liquid/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 128.5, "throughput_tps": 177, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.35, "completion_per_m": 0.5, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-lightning", "provider_name": "Darkbloom", "tag": "darkbloom/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 990, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.024999999999999998, "completion_per_m": 0.12, "input_cache_read_per_m": 0.012499999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-lightning", "provider_name": "Io Net", "tag": "io-net", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 3911.5, "throughput_tps": 8, "uptime_5m_pct": 100, "uptime_30m_pct": 96.66666666666667, "uptime_1d_pct": 99.6524761077324, "prompt_per_m": 0.046900000000000004, "completion_per_m": 0.134, "input_cache_read_per_m": 0.023450000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-lightning", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 271, "throughput_tps": 49, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.78902953586498, "prompt_per_m": 0.06, "completion_per_m": 0.16, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3.5-lightning", "provider_name": "CoreWeave", "tag": "coreweave/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 155, "throughput_tps": 134, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.07, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "sakana/sakana-namazu", "provider_name": "Sakana AI", "tag": "sakana", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.007}, {"model_id": "upstage/solar-pro4", "provider_name": "Upstage", "tag": "upstage/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1718, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "upstage/solar-pro4", "provider_name": "Upstage", "tag": "upstage", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 978, "throughput_tps": 70, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-glimmer-30b", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 1313.5, "throughput_tps": 17, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-glimmer-30b", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 452.5, "throughput_tps": 82, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.27898550724638, "prompt_per_m": 0.35, "completion_per_m": 1.5, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-1.2", "provider_name": "Meta", "tag": "meta", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2727, "throughput_tps": 234, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.0025}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Relace", "tag": "relace/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 447, "throughput_tps": 49, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0475, "completion_per_m": 0.1568, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 671, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.28, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1134, "throughput_tps": 34, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.06, "completion_per_m": 0.18, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 709, "throughput_tps": 84, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.119, "completion_per_m": 0.238, "input_cache_read_per_m": 0.0238, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "BaseTen", "tag": "baseten/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 306, "throughput_tps": 169, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.26, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "BaseTen", "tag": "baseten/fp32", "quantization": "fp32", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 271, "throughput_tps": 146, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.26, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 614, "throughput_tps": 132, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.26, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "CoreWeave", "tag": "coreweave/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 506, "throughput_tps": 73, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.13, "completion_per_m": 0.28, "input_cache_read_per_m": 0.07, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Inceptron", "tag": "inceptron/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 673, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.43119999999999997, "input_cache_read_per_m": 0.027, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1996, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13199999999999998, "completion_per_m": 0.396, "input_cache_read_per_m": 0.004200000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Wafer", "tag": "wafer/fast", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 392, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.22999999999999998, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Cohere", "tag": "cohere", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 593, "throughput_tps": 37, "uptime_5m_pct": 100, "uptime_30m_pct": 96.66666666666667, "uptime_1d_pct": 98.33333333333333, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.07, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 846, "throughput_tps": 38, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Sail Research", "tag": "sail-research/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1001, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.3, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 809, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.3, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1738, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.49874686716792, "prompt_per_m": 0.19999999999999998, "completion_per_m": 0.6, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1722, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93036211699165, "prompt_per_m": 0.22, "completion_per_m": 0.66, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 2112, "throughput_tps": 60.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.286, "completion_per_m": 0.858, "input_cache_read_per_m": 0.0091, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1824.5, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.64795144157816, "prompt_per_m": 0.352, "completion_per_m": 1.0559999999999998, "input_cache_read_per_m": 0.035199999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1905, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.82653946227234, "prompt_per_m": 0.374, "completion_per_m": 1.122, "input_cache_read_per_m": 0.037399999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1055, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.4092, "completion_per_m": 1.2275999999999998, "input_cache_read_per_m": 0.02604, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 2987.5, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1210.5, "throughput_tps": 55, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72222222222223, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.014, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1448, "throughput_tps": 49, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92163009404389, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash-0731", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 891, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.014, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "thinkingmachines/inkling-small", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 760.5, "throughput_tps": 136, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 1.2, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.7-flash", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 681, "throughput_tps": 63, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.03, "completion_per_m": 0.13, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": 0.038000000000000006, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.7-flash", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 710.5, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.034499999999999996, "completion_per_m": 0.14950000000000002, "input_cache_read_per_m": 0.0069, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3384.5, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3247, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.47715736040608, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 4124.5, "throughput_tps": 65, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.71870604781998, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2676, "throughput_tps": 50, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 0, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1934.5, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92932862190813, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-5", "provider_name": "Anthropic", "tag": "anthropic/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2064, "throughput_tps": 189, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "inclusionai/ling-3.0-flash", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 811, "throughput_tps": 131, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.020999999999999998, "completion_per_m": 0.063, "input_cache_read_per_m": 0.004200000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "inclusionai/ling-3.0-flash", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 719.5, "throughput_tps": 41, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 89.94901675163874, "prompt_per_m": 0.06, "completion_per_m": 0.18, "input_cache_read_per_m": 0.012, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "poolside/laguna-s-2.1", "provider_name": "Poolside", "tag": "poolside/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 504, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09, "completion_per_m": 0.18, "input_cache_read_per_m": 0.009, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 7000.5, "throughput_tps": 38, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 80.73394495412845, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0208333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3340, "throughput_tps": 148, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.375, "completion_per_m": 1.875, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": 0.0208333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.875, "web_search_usd": 0.014, "image_usd": 3.75e-07, "audio_usd": 3.75e-07}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1691, "throughput_tps": 114, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.75, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.75, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 7.5e-07}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1454.5, "throughput_tps": 104, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.75, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.75, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 7.5e-07}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.8250000000000001, "completion_per_m": 4.125, "input_cache_read_per_m": 0.0825, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.125, "web_search_usd": 0.014, "image_usd": 8.25e-07, "audio_usd": 8.25e-07}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1781, "throughput_tps": 158, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.35, "completion_per_m": 6.75, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": 0.075, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.75, "web_search_usd": 0.014, "image_usd": 1.35e-06, "audio_usd": 1.35e-06}, {"model_id": "google/gemini-3.6-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1691, "throughput_tps": 187, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.35, "completion_per_m": 6.75, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": 0.075, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.75, "web_search_usd": 0.014, "image_usd": 1.35e-06, "audio_usd": 1.35e-06}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 6659, "throughput_tps": 15, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.28263988522238, "prompt_per_m": 0.15, "completion_per_m": 1.25, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.25, "web_search_usd": 0.014, "image_usd": 1.5e-07, "audio_usd": 1.5e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 911, "throughput_tps": 173, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 1.25, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.25, "web_search_usd": 0.014, "image_usd": 1.5e-07, "audio_usd": 1.5e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 679, "throughput_tps": 128, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.5, "web_search_usd": 0.014, "image_usd": 3e-07, "audio_usd": 3e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 587, "throughput_tps": 119, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.5, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.5, "web_search_usd": 0.014, "image_usd": 3e-07, "audio_usd": 3e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google", "tag": "google-vertex/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 743.5, "throughput_tps": 134, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.33, "completion_per_m": 2.75, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.75, "web_search_usd": 0.014, "image_usd": 3.3e-07, "audio_usd": 3.3e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1124, "throughput_tps": 204.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.33, "completion_per_m": 2.75, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.75, "web_search_usd": 0.014, "image_usd": 3.3e-07, "audio_usd": 3.3e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 734, "throughput_tps": 135, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.54, "completion_per_m": 4.5, "input_cache_read_per_m": 0.054, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.5, "web_search_usd": 0.014, "image_usd": 5.4e-07, "audio_usd": 5.4e-07}, {"model_id": "google/gemini-3.5-flash-lite", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1077.5, "throughput_tps": 124, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.54, "completion_per_m": 4.5, "input_cache_read_per_m": 0.054, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.5, "web_search_usd": 0.014, "image_usd": 5.4e-07, "audio_usd": 5.4e-07}, {"model_id": "meituan/longcat-2.0", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048756, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1784, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92242048099301, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.006, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "thinkingmachines/inkling", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 471859, "max_prompt_tokens": null, "latency_ms": 438, "throughput_tps": 84, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.15188897455667, "prompt_per_m": 1.0, "completion_per_m": 4.05, "input_cache_read_per_m": 0.16999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Wafer", "tag": "wafer", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 559, "throughput_tps": 90, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 11.5, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Relace", "tag": "relace/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1990.5, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93050729673384, "prompt_per_m": 0.151, "completion_per_m": 10.5634, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Sail Research", "tag": "sail-research/fp4/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 808, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.22999999999999998, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11499999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1375.5, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.22999999999999998, "completion_per_m": 11.0, "input_cache_read_per_m": 0.11499999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "InferenceNet", "tag": "inference-net/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 706, "throughput_tps": 76, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.23900000000000002, "completion_per_m": 10.8, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 775, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.23900000000000002, "completion_per_m": 10.8, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Wafer", "tag": "wafer/us", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 658, "throughput_tps": 94, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.36, "completion_per_m": 11.9, "input_cache_read_per_m": 0.35900000000000004, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "InferenceNet", "tag": "inference-net/us/fast", "quantization": "fp4", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 861, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 11.879999999999999, "input_cache_read_per_m": 0.35, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "InferenceNet", "tag": "inference-net/fast", "quantization": "fp4", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 692.5, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 11.879999999999999, "input_cache_read_per_m": 0.35, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Wafer", "tag": "wafer/fast", "quantization": "mxfp4", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 625, "throughput_tps": 104, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 22.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Makora", "tag": "makora/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1379.5, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.63031423290202, "prompt_per_m": 0.65, "completion_per_m": 15.0, "input_cache_read_per_m": 0.22999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "AkashML", "tag": "akashml/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1198, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.37837837837839, "prompt_per_m": 1.2, "completion_per_m": 14.0, "input_cache_read_per_m": 1.2, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Decart", "tag": "decart/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1129, "throughput_tps": 89, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.7624703087886, "prompt_per_m": 1.6500000000000001, "completion_per_m": 8.25, "input_cache_read_per_m": 0.165, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Morph", "tag": "morph/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2370, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.806, "completion_per_m": 15.157, "input_cache_read_per_m": 0.191, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Chutes", "tag": "chutes/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65535, "max_prompt_tokens": null, "latency_ms": 3215.5, "throughput_tps": 22, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.85, "completion_per_m": 9.5, "input_cache_read_per_m": 0.185, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Fireworks", "tag": "fireworks/spot", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1087, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.41288433382138, "prompt_per_m": 2.0999999999999996, "completion_per_m": 10.5, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1069, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.5500000000000003, "completion_per_m": 12.75, "input_cache_read_per_m": 0.255, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2284.5, "throughput_tps": 37, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.5500000000000003, "completion_per_m": 12.95, "input_cache_read_per_m": 0.255, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "DeepInfra", "tag": "deepinfra/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1255, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.8499999999999996, "completion_per_m": 14.25, "input_cache_read_per_m": 0.28500000000000003, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "ParetoAlpha", "tag": "pareto-alpha/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 10683, "throughput_tps": 12, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 98.59154929577466, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-2", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1546, "throughput_tps": 63, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.96673189823875, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": 3.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 542, "throughput_tps": 85, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.18625678119349, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Modal", "tag": "modal/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1376, "throughput_tps": 79, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1557, "throughput_tps": 36, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.21283783783784, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1069.5, "throughput_tps": 50, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 98.95287958115183, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "BaseTen", "tag": "baseten/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 2989, "throughput_tps": 44, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Moonshot AI", "tag": "moonshotai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 6152, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2233, "throughput_tps": 34, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.28571428571429, "prompt_per_m": 3.45, "completion_per_m": 17.25, "input_cache_read_per_m": 0.345, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Fireworks", "tag": "fireworks/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 81.07074569789675, "prompt_per_m": 4.5, "completion_per_m": 22.5, "input_cache_read_per_m": 0.44999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k3", "provider_name": "Fireworks", "tag": "fireworks/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 993.5, "throughput_tps": 92, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.94894894894894, "prompt_per_m": 4.5, "completion_per_m": 22.5, "input_cache_read_per_m": 0.44999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "meta/muse-spark-1.1", "provider_name": "Meta", "tag": "meta", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1827, "throughput_tps": 196, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 4.25, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.0025}, {"model_id": "openai/gpt-5.6-luna-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 111333, "throughput_tps": 114, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.6, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 14542.5, "throughput_tps": 128, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.2, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": 0.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7307, "throughput_tps": 101, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.2, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": 0.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 6578, "throughput_tps": 158, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.22, "completion_per_m": 1.32, "input_cache_read_per_m": 0.022, "input_cache_write_per_m": 0.275, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.39999999999999997, "completion_per_m": 2.4, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": 0.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2547.5, "throughput_tps": 36, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.30555555555556, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.6, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": 0.125, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3765, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.2, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": 0.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1758.5, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.2, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": 0.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1740.5, "throughput_tps": 100, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.22, "completion_per_m": 1.32, "input_cache_read_per_m": 0.022, "input_cache_write_per_m": 0.275, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 985, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.9250936329588, "prompt_per_m": 0.22, "completion_per_m": 1.32, "input_cache_read_per_m": 0.022, "input_cache_write_per_m": 0.275, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1532, "throughput_tps": 144, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.22, "completion_per_m": 1.32, "input_cache_read_per_m": 0.022, "input_cache_write_per_m": 0.275, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-luna", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2385, "throughput_tps": 141.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 2.4, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": 0.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 6524, "throughput_tps": 81, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2503, "throughput_tps": 58, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 13.200000000000001, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 24.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2304.5, "throughput_tps": 94, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72222222222223, "prompt_per_m": 1.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 1.25, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 5214, "throughput_tps": 82, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.88734353268428, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2305, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2057, "throughput_tps": 71, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 13.200000000000001, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1598.5, "throughput_tps": 102.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.2, "completion_per_m": 13.200000000000001, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 13.200000000000001, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-terra", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1040, "throughput_tps": 84, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 24.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3320, "throughput_tps": 54, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 15923.5, "throughput_tps": 124, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol-pro", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1768, "throughput_tps": 39, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.44, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol-pro", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 8.0, "completion_per_m": 40.0, "input_cache_read_per_m": 0.7999999999999999, "input_cache_write_per_m": 10.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 10096, "throughput_tps": 65, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 4659.5, "throughput_tps": 58, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.12239221140473, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3109, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.0, "completion_per_m": 20.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": 5.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3458, "throughput_tps": 60.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.44, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3274, "throughput_tps": 73.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.44, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 4.4, "completion_per_m": 22.0, "input_cache_read_per_m": 0.44, "input_cache_write_per_m": 5.5, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.6-sol", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1768, "throughput_tps": 51, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 8.0, "completion_per_m": 40.0, "input_cache_read_per_m": 0.7999999999999999, "input_cache_write_per_m": 10.0, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "x-ai/grok-4.5", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1583, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.5", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": 1493, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.5", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.6, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.5", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 500000, "max_completion_tokens": 450000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 4.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.6, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "aion-labs/aion-3.0-mini", "provider_name": "AionLabs", "tag": "aion-labs", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 739, "throughput_tps": 55, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.7, "completion_per_m": 1.4, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "aion-labs/aion-3.0", "provider_name": "AionLabs", "tag": "aion-labs", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1423, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.76331360946745, "prompt_per_m": 3.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.75, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy3", "provider_name": "Tencent", "tag": "tencent/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3099.5, "throughput_tps": 34, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13199999999999998, "completion_per_m": 0.5279999999999999, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy3", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2234.5, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.58, "input_cache_read_per_m": 0.035, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy3", "provider_name": "GMICloud", "tag": "gmicloud/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2137, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.58, "input_cache_read_per_m": 0.035, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy3", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1636, "throughput_tps": 29, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.64, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy3", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1480, "throughput_tps": 89, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 0.7999999999999999, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "poolside/laguna-xs-2.1", "provider_name": "Poolside", "tag": "poolside/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 380, "throughput_tps": 104, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.06, "completion_per_m": 0.12, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1364, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1627, "throughput_tps": 66.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1312, "throughput_tps": 85, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.9252615844544, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1080, "throughput_tps": 58, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1352, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 10.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 2.5, "input_cache_write_1h_per_m": 4.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 709, "throughput_tps": 81, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2379.5, "throughput_tps": 96, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1387, "throughput_tps": 48.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.2, "completion_per_m": 11.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": 2.75, "input_cache_write_1h_per_m": 4.4, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "google/gemini-3.1-flash-lite-image", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 58982, "max_prompt_tokens": null, "latency_ms": 6779, "throughput_tps": 0, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 3e-05}, {"model_id": "google/gemini-3.1-flash-lite-image", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 58982, "max_prompt_tokens": null, "latency_ms": 7792, "throughput_tps": 0, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 77.58620689655173, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 3e-05}, {"model_id": "sakana/fugu-ultra", "provider_name": "Sakana AI", "tag": "sakana", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 8066, "throughput_tps": 20, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 30.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "google/gemini-3.1-flash-image", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 58982, "max_prompt_tokens": null, "latency_ms": 14601.5, "throughput_tps": 0, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 3.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 6e-05}, {"model_id": "google/gemini-3.1-flash-image", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 12139, "throughput_tps": 0, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 3.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 6e-05}, {"model_id": "google/gemini-3.1-flash-image", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 14627, "throughput_tps": 0, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.55, "completion_per_m": 3.3000000000000003, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 6.6e-05}, {"model_id": "google/gemini-3-pro-image", "provider_name": "Google AI Studio", "tag": "google-ai-studio/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 29245.5, "throughput_tps": 0, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 0.375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 12.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06, "image_output_usd": 0.00012}, {"model_id": "google/gemini-3-pro-image", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 21337, "throughput_tps": 0, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 0.375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 12.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06, "image_output_usd": 0.00012}, {"model_id": "z-ai/glm-5.2", "provider_name": "Relace", "tag": "relace", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1469.5, "throughput_tps": 79, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0303, "completion_per_m": 7.2203, "input_cache_read_per_m": 0.0303, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Wafer", "tag": "wafer/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 382, "throughput_tps": 139, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0341, "completion_per_m": 7.0, "input_cache_read_per_m": 0.032999999999999995, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Wafer", "tag": "wafer", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 344, "throughput_tps": 108, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19, "completion_per_m": 8.0, "input_cache_read_per_m": 0.18, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 748, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19, "completion_per_m": 8.0, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "DeepInfra", "tag": "deepinfra/fp4/flex", "quantization": "fp4", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 163840, "max_prompt_tokens": null, "latency_ms": 2264, "throughput_tps": 59, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 1.44, "input_cache_read_per_m": 0.08399999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1541.5, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.56, "completion_per_m": 1.76, "input_cache_read_per_m": 0.10400000000000001, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 163840, "max_prompt_tokens": null, "latency_ms": 1107, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5625, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.105, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Ambient", "tag": "ambient/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 182476, "max_prompt_tokens": null, "latency_ms": 835, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 2.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 422, "throughput_tps": 157, "uptime_5m_pct": 80, "uptime_30m_pct": 96.66666666666667, "uptime_1d_pct": 99.79166666666667, "prompt_per_m": 0.62, "completion_per_m": 2.42, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2036.5, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6496, "completion_per_m": 2.0416, "input_cache_read_per_m": 0.12064, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1277, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72752043596729, "prompt_per_m": 0.7, "completion_per_m": 2.2, "input_cache_read_per_m": 0.105, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1081, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.7, "completion_per_m": 2.2, "input_cache_read_per_m": 0.13, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1083, "throughput_tps": 45, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.938, "completion_per_m": 2.948, "input_cache_read_per_m": 0.17420000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 1048576, "latency_ms": 1165, "throughput_tps": 64, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.19354838709677, "prompt_per_m": 0.966, "completion_per_m": 3.036, "input_cache_read_per_m": 0.1932, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Inceptron", "tag": "inceptron/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 601, "throughput_tps": 117, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.77116704805492, "prompt_per_m": 0.9900000000000001, "completion_per_m": 4.32, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Morph", "tag": "morph/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 499, "throughput_tps": 91, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.90829694323145, "prompt_per_m": 1.054, "completion_per_m": 5.877, "input_cache_read_per_m": 0.196, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Alibaba", "tag": "alibaba/fp8/us-east-1", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 1048576, "latency_ms": 1172, "throughput_tps": 76, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.12, "completion_per_m": 3.52, "input_cache_read_per_m": 0.224, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Decart", "tag": "decart/fast", "quantization": "fp4", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 493.5, "throughput_tps": 470.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 8.0, "input_cache_read_per_m": 0.48, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 464, "throughput_tps": 140, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 88.22292323869611, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Mistral", "tag": "mistral/zdr", "quantization": "nvfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1226, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.8078541374474, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "BaseTen", "tag": "baseten/fp8/us", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1975.5, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 323, "throughput_tps": 160, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.39048285514346, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 997, "throughput_tps": 96, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "BaseTen", "tag": "baseten/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 1394, "throughput_tps": 92, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1703, "throughput_tps": 73, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2126.5, "throughput_tps": 57, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 595, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72850678733032, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Friendli", "tag": "friendli", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 402, "throughput_tps": 135, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1315, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Mistral", "tag": "mistral/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.54, "completion_per_m": 4.84, "input_cache_read_per_m": 0.154, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "BaseTen", "tag": "baseten/us/fast", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 411, "throughput_tps": 125, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86648865153538, "prompt_per_m": 2.0999999999999996, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "BaseTen", "tag": "baseten/fast", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 262144, "max_prompt_tokens": null, "latency_ms": 409.5, "throughput_tps": 136, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0999999999999996, "completion_per_m": 6.6000000000000005, "input_cache_read_per_m": 0.21, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Baidu", "tag": "baidu/fast", "quantization": "fp4", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 820, "throughput_tps": 106, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.25, "completion_per_m": 7.880000000000001, "input_cache_read_per_m": 0.56, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.2", "provider_name": "Alibaba", "tag": "alibaba/fast", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 1048576, "latency_ms": 912.5, "throughput_tps": 81, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.22178988326849, "prompt_per_m": 2.31, "completion_per_m": 7.26, "input_cache_read_per_m": 0.46199999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Inceptron", "tag": "inceptron/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 957, "throughput_tps": 56.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.56, "completion_per_m": 3.1, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "CoreWeave", "tag": "coreweave/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1892, "throughput_tps": 20, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.39889196675901, "prompt_per_m": 0.6, "completion_per_m": 3.0, "input_cache_read_per_m": 0.12, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "StreamLake", "tag": "streamlake", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 32000, "max_prompt_tokens": null, "latency_ms": 1660.5, "throughput_tps": 49.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.7124999999999999, "completion_per_m": 3.0, "input_cache_read_per_m": 0.14250000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Venice", "tag": "venice/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2088.5, "throughput_tps": 47, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.5, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1011, "throughput_tps": 25.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.85916, "completion_per_m": 3.8, "input_cache_read_per_m": 0.17993, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Novita", "tag": "novita/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 4203, "throughput_tps": 39, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.912, "completion_per_m": 3.84, "input_cache_read_per_m": 0.18239999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1716, "throughput_tps": 14, "uptime_5m_pct": null, "uptime_30m_pct": 70, "uptime_1d_pct": 96.18320610687023, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 5066.5, "throughput_tps": 50, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": 229376, "latency_ms": 1597.5, "throughput_tps": 61, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 787, "throughput_tps": 35, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Moonshot AI", "tag": "moonshotai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1763, "throughput_tps": 51, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.19, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.7-code", "provider_name": "Moonshot AI", "tag": "moonshotai/highspeed", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2282, "throughput_tps": 130, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.9, "completion_per_m": 8.0, "input_cache_read_per_m": 0.38, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "anthropic/claude-fable-5", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 6758, "throughput_tps": 45, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 4507, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-fable-5", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 11.0, "completion_per_m": 55.0, "input_cache_read_per_m": 1.1, "input_cache_write_per_m": 13.75, "input_cache_write_1h_per_m": 22.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "nvidia/nemotron-3.5-content-safety", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 254, "throughput_tps": 184, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 98.2532751091703, "prompt_per_m": 0.19999999999999998, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-ultra-550b-a55b", "provider_name": "DeepInfra", "tag": "deepinfra/fp4/flex", "quantization": "fp4", "service_tier": "flex", "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 2528.5, "throughput_tps": 51, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 1.76, "input_cache_read_per_m": 0.08, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-ultra-550b-a55b", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 1427, "throughput_tps": 53, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.57386363636364, "prompt_per_m": 0.5, "completion_per_m": 2.2, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-ultra-550b-a55b", "provider_name": "BaseTen", "tag": "baseten/fp4/us", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 202800, "max_completion_tokens": 182520, "max_prompt_tokens": null, "latency_ms": 277, "throughput_tps": 116, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 87.3229461756374, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": 0.12, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-ultra-550b-a55b", "provider_name": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 202800, "max_completion_tokens": 182520, "max_prompt_tokens": null, "latency_ms": 278, "throughput_tps": 112, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 90.28189910979229, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": 0.12, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-ultra-550b-a55b", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 256000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 3169.5, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 74.07407407407408, "uptime_1d_pct": 65.20351157222666, "prompt_per_m": 0.625, "completion_per_m": 3.125, "input_cache_read_per_m": 0.1875, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.7-plus", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1599, "throughput_tps": 41, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.32, "completion_per_m": 1.28, "input_cache_read_per_m": 0.064, "input_cache_write_per_m": 0.39999999999999997, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.7-plus", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1375, "throughput_tps": 41, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.32, "completion_per_m": 1.28, "input_cache_read_per_m": 0.064, "input_cache_write_per_m": 0.39999999999999997, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/flex", "quantization": "fp8", "service_tier": "flex", "status": 0, "context_length": 524288, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 89.51612903225806, "prompt_per_m": 0.224, "completion_per_m": 0.88, "input_cache_read_per_m": 0.0448, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 311, "throughput_tps": 256, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.22999999999999998, "completion_per_m": 0.96, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 8571, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 76.91326530612244, "prompt_per_m": 0.24, "completion_per_m": 0.96, "input_cache_read_per_m": 0.048, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1922, "throughput_tps": 23, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.48979591836735, "prompt_per_m": 0.28, "completion_per_m": 1.1, "input_cache_read_per_m": 0.056, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 512000, "max_prompt_tokens": null, "latency_ms": 3393, "throughput_tps": 57.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.50738916256158, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1088, "throughput_tps": 26, "uptime_5m_pct": 100, "uptime_30m_pct": 95, "uptime_1d_pct": 98.25535289452814, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 471859, "max_prompt_tokens": null, "latency_ms": 605, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 939, "throughput_tps": 113, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.67170953101362, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 524300, "max_completion_tokens": 524288, "max_prompt_tokens": null, "latency_ms": 1371, "throughput_tps": 120, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.85683607730851, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1732, "throughput_tps": 82, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92313604919293, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "Minimax", "tag": "minimax", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 524288, "max_completion_tokens": 512000, "max_prompt_tokens": 524288, "latency_ms": 1384, "throughput_tps": 93.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "ModelRun", "tag": "modelrun/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 494, "throughput_tps": 103, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.69858945805494, "prompt_per_m": 0.3, "completion_per_m": 1.3, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m3", "provider_name": "Mara", "tag": "mara", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 5608.5, "throughput_tps": 15.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "stepfun/step-3.7-flash", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 256000, "max_prompt_tokens": null, "latency_ms": 3207.5, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.15, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "stepfun/step-3.7-flash", "provider_name": "StepFun", "tag": "stepfun/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": 5010, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.15, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 851.5, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 0, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2245, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.19028340080972, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3050, "throughput_tps": 75, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.46236559139786, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1071, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.68578161822467, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1218.5, "throughput_tps": 100, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.8", "provider_name": "Anthropic", "tag": "anthropic/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 582, "throughput_tps": 174.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 10.0, "completion_per_m": 50.0, "input_cache_read_per_m": 1.0, "input_cache_write_per_m": 12.5, "input_cache_write_1h_per_m": 20.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "qwen/qwen3.7-max", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1215, "throughput_tps": 73.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.475, "completion_per_m": 4.425, "input_cache_read_per_m": 0.295, "input_cache_write_per_m": 1.84375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.7-max", "provider_name": "Alibaba", "tag": "alibaba/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 131072, "max_prompt_tokens": 983616, "latency_ms": 1581, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "x-ai/grok-build-0.1", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": 1177, "throughput_tps": 143, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 2.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-build-0.1", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": 1069, "throughput_tps": 158, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 2.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-build-0.1", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 4.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-build-0.1", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.0, "completion_per_m": 4.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 94.73684210526315, "prompt_per_m": 0.75, "completion_per_m": 4.5, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.5, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 1.5e-06}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 893, "throughput_tps": 84.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 4.5, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 4.5, "web_search_usd": 0.014, "image_usd": 7.5e-07, "audio_usd": 1.5e-06}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1619, "throughput_tps": 124, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.5, "completion_per_m": 9.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 9.0, "web_search_usd": 0.014, "image_usd": 1.5e-06, "audio_usd": 3e-06}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1380, "throughput_tps": 129, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.91204925241864, "prompt_per_m": 1.5, "completion_per_m": 9.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 9.0, "web_search_usd": 0.014, "image_usd": 1.5e-06, "audio_usd": 3e-06}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.6500000000000001, "completion_per_m": 9.9, "input_cache_read_per_m": 0.165, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 9.9, "web_search_usd": 0.014, "image_usd": 1.65e-06, "audio_usd": 3.3e-06}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1584, "throughput_tps": 79, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.7, "completion_per_m": 16.2, "input_cache_read_per_m": 0.27, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 16.2, "web_search_usd": 0.014, "image_usd": 2.7e-06, "audio_usd": 5.4e-06}, {"model_id": "google/gemini-3.5-flash", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.7, "completion_per_m": 16.2, "input_cache_read_per_m": 0.27, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 16.2, "web_search_usd": 0.014, "image_usd": 2.7e-06, "audio_usd": 5.4e-06}, {"model_id": "perceptron/perceptron-mk1", "provider_name": "Perceptron", "tag": "perceptron", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 32768, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 1548, "throughput_tps": 9, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 1.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 18222.5, "throughput_tps": 25, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 62.42424242424243, "prompt_per_m": 0.125, "completion_per_m": 0.75, "input_cache_read_per_m": 0.012499999999999999, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 0.75, "web_search_usd": 0.014, "image_usd": 1.25e-07, "audio_usd": 2.5e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 591, "throughput_tps": 93, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.125, "completion_per_m": 0.75, "input_cache_read_per_m": 0.012499999999999999, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 0.75, "web_search_usd": 0.014, "image_usd": 1.25e-07, "audio_usd": 2.5e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 609.5, "throughput_tps": 231, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.5, "web_search_usd": 0.014, "image_usd": 2.5e-07, "audio_usd": 5e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 757, "throughput_tps": 142.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.5, "web_search_usd": 0.014, "image_usd": 2.5e-07, "audio_usd": 5e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google", "tag": "google-vertex/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 633, "throughput_tps": 115, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.275, "completion_per_m": 1.6500000000000001, "input_cache_read_per_m": 0.0275, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.6500000000000001, "web_search_usd": 0.014, "image_usd": 2.75e-07, "audio_usd": 5.5e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 721, "throughput_tps": 91, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.275, "completion_per_m": 1.6500000000000001, "input_cache_read_per_m": 0.0275, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.6500000000000001, "web_search_usd": 0.014, "image_usd": 2.75e-07, "audio_usd": 5.5e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1030, "throughput_tps": 119, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 2.7, "input_cache_read_per_m": 0.045, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.7, "web_search_usd": 0.014, "image_usd": 4.5e-07, "audio_usd": 9e-07}, {"model_id": "google/gemini-3.1-flash-lite", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 625, "throughput_tps": 113, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 2.7, "input_cache_read_per_m": 0.045, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.7, "web_search_usd": 0.014, "image_usd": 4.5e-07, "audio_usd": 9e-07}, {"model_id": "x-ai/grok-4.3", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 900000, "max_prompt_tokens": null, "latency_ms": 1096, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 95.68904593639576, "prompt_per_m": 1.25, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.3", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 900000, "max_prompt_tokens": null, "latency_ms": 1306, "throughput_tps": 76, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.19444444444444, "prompt_per_m": 1.25, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.3", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 900000, "max_prompt_tokens": null, "latency_ms": 485, "throughput_tps": 52, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 5.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.3", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1000000, "max_completion_tokens": 900000, "max_prompt_tokens": null, "latency_ms": 513, "throughput_tps": 70, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 5.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "mistralai/mistral-medium-3-5", "provider_name": "Mistral", "tag": "mistral/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": 450, "throughput_tps": 138, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.5, "completion_per_m": 7.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-medium-3-5", "provider_name": "Mistral", "tag": "mistral", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": 445, "throughput_tps": 123, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86807387862797, "prompt_per_m": 1.5, "completion_per_m": 7.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-medium-3-5", "provider_name": "Mistral", "tag": "mistral/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.6500000000000001, "completion_per_m": 8.25, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-plus-20260420", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 1090, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": null, "input_cache_write_per_m": 0.375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-flash", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 605, "throughput_tps": 71, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.65253648366922, "prompt_per_m": 0.1875, "completion_per_m": 1.125, "input_cache_read_per_m": null, "input_cache_write_per_m": 0.234375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "Darkbloom", "tag": "darkbloom/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 2496, "throughput_tps": 50, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.7, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 574, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.8999999999999999, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 670, "throughput_tps": 112, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.8999999999999999, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 784, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.08362369337979, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.95, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "CoreWeave", "tag": "coreweave/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 559.5, "throughput_tps": 90, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.9302649930265, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.95, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "DekaLLM", "tag": "dekallm", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 966, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 92.12827988338192, "prompt_per_m": 0.09999999999999999, "completion_per_m": 1.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 553, "throughput_tps": 105, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 96.96969696969697, "prompt_per_m": 0.09999999999999999, "completion_per_m": 1.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 778.5, "throughput_tps": 126, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.22813036020584, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.27, "input_cache_read_per_m": 0.056, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 971, "throughput_tps": 45, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 76.47058823529412, "prompt_per_m": 0.24, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-35b-a3b", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 550, "throughput_tps": 113, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 99.31856899488926, "prompt_per_m": 0.25, "completion_per_m": 1.25, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 464, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.4979079497908, "prompt_per_m": 0.19999999999999998, "completion_per_m": 3.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "Chutes", "tag": "chutes/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1657, "throughput_tps": 30, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 74.70288624787777, "prompt_per_m": 0.25, "completion_per_m": 2.0, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1051, "throughput_tps": 29, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 83.61774744027304, "prompt_per_m": 0.3, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 81920, "max_prompt_tokens": null, "latency_ms": 550, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.3257698541329, "prompt_per_m": 0.32, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 262140, "max_prompt_tokens": null, "latency_ms": 1576, "throughput_tps": 26, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 92.16589861751152, "prompt_per_m": 0.32, "completion_per_m": 3.25, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 655.5, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.89603960396039, "prompt_per_m": 0.325, "completion_per_m": 3.25, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-27b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": 258048, "latency_ms": 767, "throughput_tps": 47, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 2.7, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-5.5-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 15.0, "completion_per_m": 90.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3698, "throughput_tps": 13.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 30.0, "completion_per_m": 180.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2976, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.49238578680203, "prompt_per_m": 2.5, "completion_per_m": 15.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 5197, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 95.65217391304348, "uptime_1d_pct": 98.59278803869833, "prompt_per_m": 5.0, "completion_per_m": 30.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2461.5, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 30.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 33.0, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 33.0, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 33.0, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.5", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 12.5, "completion_per_m": 75.0, "input_cache_read_per_m": 1.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1427, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.875394, "completion_per_m": 1.750788, "input_cache_read_per_m": 0.0729495, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Relace", "tag": "relace/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 837, "throughput_tps": 78, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.8999999999999999, "completion_per_m": 1.5, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 2543.5, "throughput_tps": 24, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72183588317107, "prompt_per_m": 0.9569999999999999, "completion_per_m": 1.9139999999999997, "input_cache_read_per_m": 0.07975, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 994, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.044, "completion_per_m": 2.088, "input_cache_read_per_m": 0.20879999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1231, "throughput_tps": 41, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.43820224719101, "prompt_per_m": 1.15, "completion_per_m": 2.5500000000000003, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 881.5, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.3, "completion_per_m": 2.6, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": 1000000, "latency_ms": 1825, "throughput_tps": 49, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.94339622641509, "prompt_per_m": 1.4160000000000001, "completion_per_m": 2.8320000000000003, "input_cache_read_per_m": 0.118, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1706, "throughput_tps": 33, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72144846796658, "prompt_per_m": 1.5016200000000002, "completion_per_m": 3.1350000000000002, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Alibaba", "tag": "alibaba/fp8/us-east-1", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": 1000000, "latency_ms": 1730.5, "throughput_tps": 41, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.56, "completion_per_m": 3.12, "input_cache_read_per_m": 0.13, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 2093, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.09722222222223, "prompt_per_m": 1.5999999999999999, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": 0.135, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1676, "throughput_tps": 34, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.6500000000000001, "completion_per_m": 3.3009999999999997, "input_cache_read_per_m": 0.33, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1608, "throughput_tps": 33, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 98.89705882352942, "prompt_per_m": 1.68, "completion_per_m": 3.38, "input_cache_read_per_m": 0.13, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1198, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93041057759221, "prompt_per_m": 1.69, "completion_per_m": 3.38, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Crusoe", "tag": "crusoe/fp8", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1076.5, "throughput_tps": 49, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 96.91923397169026, "prompt_per_m": 1.74, "completion_per_m": 3.48, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-pro", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 2072.5, "throughput_tps": 77, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.91, "completion_per_m": 3.8299999999999996, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Relace", "tag": "relace/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 501, "throughput_tps": 102, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.44999999999999996, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1024000, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1612.5, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.07, "completion_per_m": 0.14, "input_cache_read_per_m": 0.014, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 4861, "throughput_tps": 17, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09, "completion_per_m": 0.18, "input_cache_read_per_m": 0.018, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048575, "max_completion_tokens": 943717, "max_prompt_tokens": null, "latency_ms": 1959, "throughput_tps": 45, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.091, "completion_per_m": 0.182, "input_cache_read_per_m": 0.0182, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1775.5, "throughput_tps": 26, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.0966, "completion_per_m": 0.1925, "input_cache_read_per_m": 0.0196, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1163, "throughput_tps": 11, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.098, "completion_per_m": 0.196, "input_cache_read_per_m": 0.0196, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Fireworks", "tag": "fireworks", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 1261.5, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 76.55068078668684, "prompt_per_m": 0.105, "completion_per_m": 0.21, "input_cache_read_per_m": 0.020999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 1372, "throughput_tps": 9, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.91666666666666, "prompt_per_m": 0.13, "completion_per_m": 0.28, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Crusoe", "tag": "crusoe/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 589, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1061, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 393216, "max_prompt_tokens": null, "latency_ms": 2070, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 953, "throughput_tps": 37, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.28, "input_cache_read_per_m": 0.07, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Alibaba", "tag": "alibaba/fp8/us-east-1", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 1000000, "max_completion_tokens": 393216, "max_prompt_tokens": 1000000, "latency_ms": 2540, "throughput_tps": 72, "uptime_5m_pct": 80, "uptime_30m_pct": 86.66666666666667, "uptime_1d_pct": 88.3866481223922, "prompt_per_m": 0.15, "completion_per_m": 0.3, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 5439, "throughput_tps": 15, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.98033503277495, "prompt_per_m": 0.19, "completion_per_m": 0.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 384000, "max_prompt_tokens": null, "latency_ms": 1633.5, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 89.24812030075188, "prompt_per_m": 0.21, "completion_per_m": 0.56, "input_cache_read_per_m": 0.031, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Wafer", "tag": "wafer/mxfp4", "quantization": "mxfp4", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 943718, "max_prompt_tokens": null, "latency_ms": 452, "throughput_tps": 81, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 0.16999999999999998, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "deepseek/deepseek-v4-flash", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 384000, "max_completion_tokens": 345600, "max_prompt_tokens": null, "latency_ms": 992, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44, "completion_per_m": 1.32, "input_cache_read_per_m": 0.014, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "tencent/hy3-preview", "provider_name": "GMICloud", "tag": "gmicloud/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2148, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.16492693110646, "prompt_per_m": 0.18, "completion_per_m": 0.6, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.5-pro", "provider_name": "GMICloud", "tag": "gmicloud/bf16", "quantization": "bf16", "service_tier": null, "status": -5, "context_length": 1050000, "max_completion_tokens": 945000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": 0, "uptime_30m_pct": 0, "uptime_1d_pct": 0, "prompt_per_m": 0.3045, "completion_per_m": 0.609, "input_cache_read_per_m": 0.0028, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.5-pro", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": -5, "context_length": 1024000, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 48579.5, "throughput_tps": 18, "uptime_5m_pct": null, "uptime_30m_pct": 0, "uptime_1d_pct": 76.41843971631207, "prompt_per_m": 0.435, "completion_per_m": 0.87, "input_cache_read_per_m": 0.0036, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.5-pro", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1260.5, "throughput_tps": 17, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.77468706536857, "prompt_per_m": 0.48, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.096, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.5", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": -5, "context_length": 1050000, "max_completion_tokens": 945000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": 0, "uptime_30m_pct": 0, "uptime_1d_pct": 58.24175824175825, "prompt_per_m": 0.119, "completion_per_m": 0.238, "input_cache_read_per_m": 0.00255, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "xiaomi/mimo-v2.5", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2136, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 2.0, "input_cache_read_per_m": 0.08, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-5.4-image-2", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 272000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 79978, "throughput_tps": 0, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.9213217938631, "prompt_per_m": 8.0, "completion_per_m": 15.0, "input_cache_read_per_m": 2.0, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01, "image_output_usd": 3e-05}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Chutes", "tag": "chutes/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65535, "max_prompt_tokens": null, "latency_ms": 1666, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.89473684210526, "prompt_per_m": 0.39, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.039, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 657, "throughput_tps": 33, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5700000000000001, "completion_per_m": 2.4, "input_cache_read_per_m": 0.114, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Inceptron", "tag": "inceptron/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 494, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.585, "completion_per_m": 3.5, "input_cache_read_per_m": 0.117, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": 1569, "throughput_tps": 36, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 91.22807017543859, "prompt_per_m": 0.5984999999999999, "completion_per_m": 2.52, "input_cache_read_per_m": 0.1008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 399, "throughput_tps": 110, "uptime_5m_pct": 80, "uptime_30m_pct": 96.66666666666667, "uptime_1d_pct": 99.30507296733843, "prompt_per_m": 0.65, "completion_per_m": 3.41, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Crusoe", "tag": "crusoe/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 445, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.01892081289418, "prompt_per_m": 0.7, "completion_per_m": 3.5, "input_cache_read_per_m": 0.35, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 10762, "throughput_tps": 13.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.83948635634029, "prompt_per_m": 0.75, "completion_per_m": 3.5, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Venice", "tag": "venice/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1974, "throughput_tps": 44, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 98.86877828054298, "prompt_per_m": 0.75, "completion_per_m": 3.5, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Parasail", "tag": "parasail/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 746, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 3.5, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1097, "throughput_tps": 21.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.77, "completion_per_m": 3.4, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1986, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.7999999999999999, "completion_per_m": 3.4, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 0, "prompt_per_m": 0.855, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": 0.144, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Baidu", "tag": "baidu/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 848.5, "throughput_tps": 74, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.7864768683274, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "AtlasCloud", "tag": "atlas-cloud/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1251, "throughput_tps": 31.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 697, "throughput_tps": 36.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Moonshot AI", "tag": "moonshotai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2391.5, "throughput_tps": 47, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 96.01100412654745, "prompt_per_m": 0.95, "completion_per_m": 4.0, "input_cache_read_per_m": 0.16, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.6", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1283, "throughput_tps": 31.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 95.65217391304348, "prompt_per_m": 1.0899999999999999, "completion_per_m": 4.6, "input_cache_read_per_m": 0.37, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 855.5, "throughput_tps": 49, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86013986013987, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 0, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1773, "throughput_tps": 80, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.78542510121457, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1294, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 614.5, "throughput_tps": 41, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 98.44961240310077, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Google", "tag": "google-vertex/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.7", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "z-ai/glm-5.1", "provider_name": "Chutes", "tag": "chutes/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 65535, "max_prompt_tokens": null, "latency_ms": 2222, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.51140065146579, "prompt_per_m": 0.8999999999999999, "completion_per_m": 2.9000000000000004, "input_cache_read_per_m": 0.09, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 200000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1550.5, "throughput_tps": 43, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.92952783650459, "prompt_per_m": 0.966, "completion_per_m": 3.036, "input_cache_read_per_m": 0.1794, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1373.5, "throughput_tps": 65, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.19, "completion_per_m": 3.74, "input_cache_read_per_m": 0.6, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2414, "throughput_tps": 32.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.21, "completion_per_m": 4.199999999999999, "input_cache_read_per_m": 0.6, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 182476, "max_prompt_tokens": null, "latency_ms": 1148, "throughput_tps": 66, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.26, "completion_per_m": 3.9600000000000004, "input_cache_read_per_m": 0.234, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202745, "max_completion_tokens": 131072, "max_prompt_tokens": 169984, "latency_ms": 1480, "throughput_tps": 84, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 94.5945945945946, "prompt_per_m": 1.33, "completion_per_m": 4.18, "input_cache_read_per_m": 0.24699999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2076.5, "throughput_tps": 51, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.38, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Nebius", "tag": "nebius/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 182476, "max_prompt_tokens": null, "latency_ms": 451, "throughput_tps": 35, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 963, "throughput_tps": 69.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 182476, "max_prompt_tokens": null, "latency_ms": 1392, "throughput_tps": 55, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Friendli", "tag": "friendli", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 182476, "max_prompt_tokens": null, "latency_ms": 385.5, "throughput_tps": 117, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.83805668016194, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 4152, "throughput_tps": 23, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.53307392996109, "prompt_per_m": 1.4, "completion_per_m": 4.4, "input_cache_read_per_m": 0.26, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5.1", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 200000, "max_completion_tokens": 80000, "max_prompt_tokens": null, "latency_ms": 1245, "throughput_tps": 68, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.4014, "completion_per_m": 4.4044, "input_cache_read_per_m": 0.26026, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Darkbloom", "tag": "darkbloom", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1038, "throughput_tps": 34, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.041999999999999996, "completion_per_m": 0.22, "input_cache_read_per_m": 0.020999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "DekaLLM", "tag": "dekallm/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 463, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.54166666666667, "prompt_per_m": 0.06, "completion_per_m": 0.33, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "AkashML", "tag": "akashml/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 757.5, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.69211195928753, "prompt_per_m": 0.07, "completion_per_m": 0.24, "input_cache_read_per_m": 0.046, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Makora", "tag": "makora", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 246, "throughput_tps": 147, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 0.07, "completion_per_m": 0.24, "input_cache_read_per_m": 0.046, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 445, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.07, "completion_per_m": 0.33999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "NextBit", "tag": "nextbit/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 299, "throughput_tps": 75.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72222222222223, "prompt_per_m": 0.0765, "completion_per_m": 0.255, "input_cache_read_per_m": 0.042499999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Io Net", "tag": "io-net/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262142, "max_completion_tokens": 235927, "max_prompt_tokens": null, "latency_ms": 638, "throughput_tps": 91, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09, "completion_per_m": 0.31, "input_cache_read_per_m": 0.041, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "PrimeIntellect", "tag": "primeintellect/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 232, "throughput_tps": 148, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93002099370189, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.3, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "CoreWeave", "tag": "coreweave/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 347, "throughput_tps": 69, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.3, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 230400, "max_prompt_tokens": null, "latency_ms": 409, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.3, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Venice", "tag": "venice/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 756, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Parasail", "tag": "parasail/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 486, "throughput_tps": 93, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Novita", "tag": "novita/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 773, "throughput_tps": 193, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.13, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1211, "throughput_tps": 27, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 94.73314606741573, "prompt_per_m": 0.14, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-26b-a4b-it", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2117, "throughput_tps": 26, "uptime_5m_pct": 100, "uptime_30m_pct": 88.46153846153845, "uptime_1d_pct": 94.39999999999999, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 261, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.65277777777779, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.33999999999999997, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Venice", "tag": "venice/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 721, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.12, "completion_per_m": 0.36, "input_cache_read_per_m": 0.09, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Chutes", "tag": "chutes/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 4356, "throughput_tps": 13, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.74301675977654, "prompt_per_m": 0.12, "completion_per_m": 0.37, "input_cache_read_per_m": 0.012, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "DeepInfra", "tag": "deepinfra/turbo", "quantization": "fp4", "service_tier": "priority", "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 770, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93055555555556, "prompt_per_m": 0.135, "completion_per_m": 0.51, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "DekaLLM", "tag": "dekallm", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1684, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.7667009249743, "prompt_per_m": 0.14, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Crusoe", "tag": "crusoe/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 262141, "max_prompt_tokens": null, "latency_ms": 483, "throughput_tps": 35, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.37456567060458, "prompt_per_m": 0.14, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Friendli", "tag": "friendli", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 558, "throughput_tps": 70, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.14, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Novita", "tag": "novita/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1160, "throughput_tps": 17, "uptime_5m_pct": 100, "uptime_30m_pct": 96.66666666666667, "uptime_1d_pct": 92.40947075208913, "prompt_per_m": 0.14, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1236, "throughput_tps": 60, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86082115518441, "prompt_per_m": 0.15, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/flex", "quantization": "fp8", "service_tier": "flex", "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2334, "throughput_tps": 22, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.16, "completion_per_m": 0.32, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 1043, "throughput_tps": 23, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "DeepInfra", "tag": "deepinfra/fp8/priority", "quantization": "fp8", "service_tier": "priority", "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1060, "throughput_tps": 22, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.69465648854961, "prompt_per_m": 0.3, "completion_per_m": 0.6, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "Io Net", "tag": "io-net", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 1636, "throughput_tps": 26, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.42857142857143, "prompt_per_m": 0.36100000000000004, "completion_per_m": 1.0925, "input_cache_read_per_m": 0.18050000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "SambaNova", "tag": "sambanova", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 3780, "throughput_tps": 98, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 95.3971119133574, "prompt_per_m": 0.38, "completion_per_m": 1.15, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "ModelRun", "tag": "modelrun/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 233, "throughput_tps": 171, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 1.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemma-4-31b-it", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1693, "throughput_tps": 7, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.03536977491962, "prompt_per_m": 0.75, "completion_per_m": 1.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.6-plus", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 1192, "throughput_tps": 40, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93036211699165, "prompt_per_m": 0.325, "completion_per_m": 1.95, "input_cache_read_per_m": null, "input_cache_write_per_m": 0.40625, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5v-turbo", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2413, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 4.0, "input_cache_read_per_m": 0.24, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "x-ai/grok-4.20-multi-agent", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": 35382, "throughput_tps": 206, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20-multi-agent", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": 21059, "throughput_tps": 237, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 57.14285714285714, "prompt_per_m": 1.25, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20-multi-agent", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.5, "completion_per_m": 5.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20-multi-agent", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": 8014, "throughput_tps": 245.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.5, "completion_per_m": 5.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20", "provider_name": "xAI", "tag": "xai/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": 948.5, "throughput_tps": 81, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20", "provider_name": "xAI", "tag": "xai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": 677, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.25, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20", "provider_name": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": 1105.5, "throughput_tps": 118.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 5.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "x-ai/grok-4.20", "provider_name": "xAI", "tag": "xai/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 2000000, "max_completion_tokens": 1800000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.5, "completion_per_m": 5.0, "input_cache_read_per_m": 0.39999999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.005}, {"model_id": "google/lyria-3-pro-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": -5, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 9350, "throughput_tps": 14, "uptime_5m_pct": 0, "uptime_30m_pct": 0, "uptime_1d_pct": 0.29784065524944153, "prompt_per_m": 0.0, "completion_per_m": 0.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/lyria-3-clip-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2447, "throughput_tps": 7, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.0, "completion_per_m": 0.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "rekaai/reka-edge", "provider_name": "Reka", "tag": "reka", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 16384, "max_completion_tokens": 14745, "max_prompt_tokens": null, "latency_ms": 428, "throughput_tps": 118.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.09999999999999999, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.7", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 196608, "max_completion_tokens": 176947, "max_prompt_tokens": null, "latency_ms": 1566.5, "throughput_tps": 18, "uptime_5m_pct": 100, "uptime_30m_pct": 95.83333333333334, "uptime_1d_pct": 97.21739130434783, "prompt_per_m": 0.21, "completion_per_m": 0.84, "input_cache_read_per_m": 0.041999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.7", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1879.5, "throughput_tps": 19, "uptime_5m_pct": 100, "uptime_30m_pct": 96, "uptime_1d_pct": 99.17423616845582, "prompt_per_m": 0.27, "completion_per_m": 1.08, "input_cache_read_per_m": 0.054, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.7", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 196608, "max_completion_tokens": 176947, "max_prompt_tokens": null, "latency_ms": 1490.5, "throughput_tps": 22, "uptime_5m_pct": null, "uptime_30m_pct": 90, "uptime_1d_pct": 99.34711643090316, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.7", "provider_name": "Minimax", "tag": "minimax", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1296, "throughput_tps": 24, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 97.6401179941003, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.7", "provider_name": "Groq", "tag": "groq", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 196608, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 308, "throughput_tps": 277, "uptime_5m_pct": 100, "uptime_30m_pct": 94.11764705882352, "uptime_1d_pct": 98.89380530973452, "prompt_per_m": 0.6, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.7", "provider_name": "Minimax", "tag": "minimax/highspeed", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1727, "throughput_tps": 32, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 90.41916167664671, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-5.4-nano", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1276, "throughput_tps": 99, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 86.88524590163934, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.625, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-nano", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3004, "throughput_tps": 63, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.25, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-nano", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 850, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.19999999999999998, "completion_per_m": 1.25, "input_cache_read_per_m": 0.02, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-nano", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.22, "completion_per_m": 1.375, "input_cache_read_per_m": 0.022, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-mini", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1210.5, "throughput_tps": 101, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.68051118210862, "prompt_per_m": 0.375, "completion_per_m": 2.25, "input_cache_read_per_m": 0.0375, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-mini", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1464, "throughput_tps": 79, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 4.5, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-mini", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 975, "throughput_tps": 108, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.75, "completion_per_m": 4.5, "input_cache_read_per_m": 0.075, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-mini", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.8250000000000001, "completion_per_m": 4.95, "input_cache_read_per_m": 0.0825, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-mini", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1070, "throughput_tps": 96, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.5, "completion_per_m": 9.0, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "mistralai/mistral-small-2603", "provider_name": "Mistral", "tag": "mistral/zdr", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": 507, "throughput_tps": 110, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-small-2603", "provider_name": "Mistral", "tag": "mistral", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": 503.5, "throughput_tps": 111, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-small-2603", "provider_name": "Mistral", "tag": "mistral/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": 946, "throughput_tps": 85, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 99.82078853046595, "prompt_per_m": 0.165, "completion_per_m": 0.66, "input_cache_read_per_m": 0.016499999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "mistralai/mistral-small-2603", "provider_name": "Mistral", "tag": "mistral/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 209715, "max_prompt_tokens": null, "latency_ms": 322, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.84227129337539, "prompt_per_m": 0.165, "completion_per_m": 0.66, "input_cache_read_per_m": 0.016499999999999997, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5-turbo", "provider_name": "Z.AI", "tag": "z-ai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 4078, "throughput_tps": 25, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 4.0, "input_cache_read_per_m": 0.24, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-super-120b-a12b", "provider_name": "DekaLLM", "tag": "dekallm/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1101, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.28876244665719, "prompt_per_m": 0.08, "completion_per_m": 0.44999999999999996, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-super-120b-a12b", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 3701, "throughput_tps": 86, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.08499999999999999, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-super-120b-a12b", "provider_name": "Crusoe", "tag": "crusoe/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 412.5, "throughput_tps": 134, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.4, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "bytedance-seed/seed-2.0-lite", "provider_name": "Seed", "tag": "seed/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1785, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 2.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-9b", "provider_name": "Darkbloom", "tag": "darkbloom/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1021, "throughput_tps": 50, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.08, "completion_per_m": 0.13, "input_cache_read_per_m": 0.04, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-9b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1347.5, "throughput_tps": 33, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 95.56737588652481, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.15, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-9b", "provider_name": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 81920, "max_prompt_tokens": null, "latency_ms": 444, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 93.48939283101683, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.15, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-9b", "provider_name": "Parasail", "tag": "parasail/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 188, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.97585954645209, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.25, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-9b", "provider_name": "PrimeIntellect", "tag": "primeintellect/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 40960, "max_prompt_tokens": null, "latency_ms": 224, "throughput_tps": 96.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.16999999999999998, "completion_per_m": 0.25, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-9b", "provider_name": "Together", "tag": "together", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 579, "throughput_tps": 83, "uptime_5m_pct": 100, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 98.95833333333334, "prompt_per_m": 0.16999999999999998, "completion_per_m": 0.25, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-5.4-pro", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 15.0, "completion_per_m": 90.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-pro", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 30.0, "completion_per_m": 180.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4-pro", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 7134, "throughput_tps": 9, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 30.0, "completion_per_m": 180.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "service_tier": "flex", "status": -2, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 8016.5, "throughput_tps": 11, "uptime_5m_pct": null, "uptime_30m_pct": 50, "uptime_1d_pct": 8.641975308641975, "prompt_per_m": 1.25, "completion_per_m": 7.5, "input_cache_read_per_m": 0.125, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 3256, "throughput_tps": 62, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 15.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 1425, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 15.0, "input_cache_read_per_m": 0.25, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "Azure", "tag": "azure/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.75, "completion_per_m": 16.5, "input_cache_read_per_m": 0.275, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "Azure", "tag": "azure/eu", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.75, "completion_per_m": 16.5, "input_cache_read_per_m": 0.275, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": 2313, "throughput_tps": 74, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 2.75, "completion_per_m": 16.5, "input_cache_read_per_m": 0.275, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.4", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1050000, "max_completion_tokens": 128000, "max_prompt_tokens": 922000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 30.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "inception/mercury-2", "provider_name": "Inception", "tag": "inception", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 50000, "max_prompt_tokens": null, "latency_ms": 2265, "throughput_tps": 392, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.01574803149606, "prompt_per_m": 0.25, "completion_per_m": 0.75, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.1-flash-lite-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 644, "throughput_tps": 111.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.125, "completion_per_m": 0.75, "input_cache_read_per_m": 0.012499999999999999, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 0.75, "web_search_usd": 0.014, "image_usd": 1.25e-07, "audio_usd": 2.5e-07}, {"model_id": "google/gemini-3.1-flash-lite-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 667, "throughput_tps": 167, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.5, "web_search_usd": 0.014, "image_usd": 2.5e-07, "audio_usd": 5e-07}, {"model_id": "google/gemini-3.1-flash-lite-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 499, "throughput_tps": 98, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.44999999999999996, "completion_per_m": 2.7, "input_cache_read_per_m": 0.045, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 2.7, "web_search_usd": 0.014, "image_usd": 4.5e-07, "audio_usd": 9e-07}, {"model_id": "bytedance-seed/seed-2.0-mini", "provider_name": "Seed", "tag": "seed/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 391, "throughput_tps": 94, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.1-flash-image-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 58982, "max_prompt_tokens": null, "latency_ms": 15715, "throughput_tps": 0, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.70631424375918, "prompt_per_m": 0.5, "completion_per_m": 3.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.014, "image_output_usd": 6e-05}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "Darkbloom", "tag": "darkbloom/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 934, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.37759336099586, "prompt_per_m": 0.065, "completion_per_m": 0.75, "input_cache_read_per_m": 0.0325, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 81920, "max_prompt_tokens": null, "latency_ms": 403, "throughput_tps": 90.5, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 98.49187935034803, "prompt_per_m": 0.14, "completion_per_m": 1.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 282, "throughput_tps": 73, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 1.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 441, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86357435197817, "prompt_per_m": 0.15, "completion_per_m": 1.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": 258048, "latency_ms": 630, "throughput_tps": 123, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.84177215189874, "prompt_per_m": 0.1625, "completion_per_m": 1.3, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 886.5, "throughput_tps": 36, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 94.5945945945946, "prompt_per_m": 0.22499999999999998, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.22499999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-35b-a3b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1093, "throughput_tps": 71, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 94.39252336448598, "prompt_per_m": 0.24, "completion_per_m": 1.7999999999999998, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-27b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": 258048, "latency_ms": 1588, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 91.66666666666666, "uptime_1d_pct": 92.51925192519252, "prompt_per_m": 0.195, "completion_per_m": 1.56, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-27b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1031.5, "throughput_tps": 25.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 79.62962962962963, "prompt_per_m": 0.25, "completion_per_m": 2.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-27b", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 81920, "max_prompt_tokens": null, "latency_ms": 773, "throughput_tps": 52, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.26, "completion_per_m": 2.6, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-27b", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1149, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.89626556016597, "prompt_per_m": 0.27, "completion_per_m": 2.16, "input_cache_read_per_m": 0.27, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-27b", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2005, "throughput_tps": 25, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 81.81818181818183, "prompt_per_m": 0.3, "completion_per_m": 2.4, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-27b", "provider_name": "Novita", "tag": "novita/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1528, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.75, "prompt_per_m": 0.3, "completion_per_m": 2.4, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-122b-a10b", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1014, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 96.89839572192514, "prompt_per_m": 0.26, "completion_per_m": 2.08, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-122b-a10b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": 258048, "latency_ms": 919, "throughput_tps": 77.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.26, "completion_per_m": 2.08, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-122b-a10b", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1328, "throughput_tps": 42.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.4, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-122b-a10b", "provider_name": "Novita", "tag": "novita/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3580, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39999999999999997, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-flash-02-23", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 513, "throughput_tps": 71, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.065, "completion_per_m": 0.26, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.1-pro-preview-customtools", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2640, "throughput_tps": 36, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 0.375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 12.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06}, {"model_id": "openai/gpt-5.3-codex", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": 272000, "latency_ms": 4499, "throughput_tps": 36, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.75, "completion_per_m": 14.0, "input_cache_read_per_m": 0.175, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.3-codex", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": 272000, "latency_ms": 2332.5, "throughput_tps": 72, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.75, "completion_per_m": 14.0, "input_cache_read_per_m": 0.175, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "openai/gpt-5.3-codex", "provider_name": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": 272000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 3.5, "completion_per_m": 28.0, "input_cache_read_per_m": 0.35, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "aion-labs/aion-2.0", "provider_name": "AionLabs", "tag": "aion-labs", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 782, "throughput_tps": 56, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.7999999999999999, "completion_per_m": 1.5999999999999999, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3.1-pro-preview", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 90270, "throughput_tps": 17, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 5.769230769230769, "prompt_per_m": 1.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 0.1875, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.0, "web_search_usd": 0.014, "image_usd": 1e-06, "audio_usd": 1e-06}, {"model_id": "google/gemini-3.1-pro-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3058.5, "throughput_tps": 95, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 6.0, "input_cache_read_per_m": 0.09999999999999999, "input_cache_write_per_m": 0.1875, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 6.0, "web_search_usd": 0.014, "image_usd": 1e-06, "audio_usd": 1e-06}, {"model_id": "google/gemini-3.1-pro-preview", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 2873, "throughput_tps": 82, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86111111111111, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 0.375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 12.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06}, {"model_id": "google/gemini-3.1-pro-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3328, "throughput_tps": 103, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.0, "completion_per_m": 12.0, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": 0.375, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 12.0, "web_search_usd": 0.014, "image_usd": 2e-06, "audio_usd": 2e-06}, {"model_id": "google/gemini-3.1-pro-preview", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 4148, "throughput_tps": 105, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.5999999999999996, "completion_per_m": 21.6, "input_cache_read_per_m": 0.36, "input_cache_write_per_m": 0.675, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 21.6, "web_search_usd": 0.014, "image_usd": 3.6e-06, "audio_usd": 3.6e-06}, {"model_id": "google/gemini-3.1-pro-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 3241, "throughput_tps": 95, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.5999999999999996, "completion_per_m": 21.6, "input_cache_read_per_m": 0.36, "input_cache_write_per_m": 0.675, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 21.6, "web_search_usd": 0.014, "image_usd": 3.6e-06, "audio_usd": 3.6e-06}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 698, "throughput_tps": 46, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": 3.75, "input_cache_write_1h_per_m": 6.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": 3.75, "input_cache_write_1h_per_m": 6.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1047, "throughput_tps": 38, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": 3.75, "input_cache_write_1h_per_m": 6.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1017, "throughput_tps": 68, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": 3.75, "input_cache_write_1h_per_m": 6.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2291.5, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 3.0, "completion_per_m": 15.0, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": 3.75, "input_cache_write_1h_per_m": 6.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 694, "throughput_tps": 40.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.3000000000000003, "completion_per_m": 16.5, "input_cache_read_per_m": 0.33, "input_cache_write_per_m": 4.125, "input_cache_write_1h_per_m": 6.6000000000000005, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1221, "throughput_tps": 50, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.3000000000000003, "completion_per_m": 16.5, "input_cache_read_per_m": 0.33, "input_cache_write_per_m": 4.125, "input_cache_write_1h_per_m": 6.6000000000000005, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 535, "throughput_tps": 47, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.3000000000000003, "completion_per_m": 16.5, "input_cache_read_per_m": 0.33, "input_cache_write_per_m": 4.125, "input_cache_write_1h_per_m": 6.6000000000000005, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-sonnet-4.6", "provider_name": "Google", "tag": "google-vertex/us-east5", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 3.3000000000000003, "completion_per_m": 16.5, "input_cache_read_per_m": 0.33, "input_cache_write_per_m": 4.125, "input_cache_write_1h_per_m": 6.6000000000000005, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "qwen/qwen3.5-plus-02-15", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 65536, "max_prompt_tokens": 983616, "latency_ms": 1031, "throughput_tps": 59, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.91126885536823, "prompt_per_m": 0.26, "completion_per_m": 1.56, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "Alibaba", "tag": "alibaba", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": 258048, "latency_ms": 1169, "throughput_tps": 57, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.39, "completion_per_m": 2.34, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 81920, "max_prompt_tokens": null, "latency_ms": 754, "throughput_tps": 64, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.62157048249763, "prompt_per_m": 0.44999999999999996, "completion_per_m": 3.0, "input_cache_read_per_m": 0.22, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1391, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": 0.3, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 876, "throughput_tps": 14, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 83.91608391608392, "prompt_per_m": 0.55, "completion_per_m": 3.5, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "Phala", "tag": "phala", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2419.5, "throughput_tps": 58, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 95.8477508650519, "prompt_per_m": 0.55, "completion_per_m": 3.5, "input_cache_read_per_m": 0.22499999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 939.5, "throughput_tps": 48, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 93.24324324324324, "prompt_per_m": 0.55, "completion_per_m": 3.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "StreamLake", "tag": "streamlake", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 64000, "max_prompt_tokens": null, "latency_ms": 2470, "throughput_tps": 65, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 97.71428571428571, "prompt_per_m": 0.6, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": 0.12, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1480.5, "throughput_tps": 49.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 78.78787878787878, "prompt_per_m": 0.6, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1266, "throughput_tps": 46, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 94.82758620689656, "prompt_per_m": 0.6, "completion_per_m": 3.5999999999999996, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "qwen/qwen3.5-397b-a17b", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1369, "throughput_tps": 43, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 95.47619047619048, "prompt_per_m": 0.75, "completion_per_m": 4.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 198000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 1478, "throughput_tps": 20, "uptime_5m_pct": 100, "uptime_30m_pct": 96.15384615384616, "uptime_1d_pct": 95.12855209742895, "prompt_per_m": 0.27, "completion_per_m": 0.95, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "StreamLake", "tag": "streamlake", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 200000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 696, "throughput_tps": 93, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.27, "completion_per_m": 1.08, "input_cache_read_per_m": 0.027, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 196608, "max_completion_tokens": 176947, "max_prompt_tokens": null, "latency_ms": 1843, "throughput_tps": 57, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.295, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 196608, "max_completion_tokens": 176947, "max_prompt_tokens": null, "latency_ms": 1119.5, "throughput_tps": 24, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 90, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 58982, "max_prompt_tokens": null, "latency_ms": 592, "throughput_tps": 74, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131100, "max_prompt_tokens": null, "latency_ms": 969.5, "throughput_tps": 39, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 97.14285714285714, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "Minimax", "tag": "minimax", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1291.5, "throughput_tps": 23, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 93.76498800959233, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.5", "provider_name": "Minimax", "tag": "minimax/highspeed", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2406, "throughput_tps": 19, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 85, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": 0.06, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 198000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2056, "throughput_tps": 59, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 1.92, "input_cache_read_per_m": 0.12, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 182476, "max_prompt_tokens": null, "latency_ms": 2478, "throughput_tps": 66, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.57983193277312, "prompt_per_m": 0.6, "completion_per_m": 1.92, "input_cache_read_per_m": 0.12, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1057, "throughput_tps": 54, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.84662576687117, "prompt_per_m": 0.7, "completion_per_m": 2.24, "input_cache_read_per_m": 0.14, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2253.5, "throughput_tps": 53, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.74070872947277, "prompt_per_m": 0.95, "completion_per_m": 2.5500000000000003, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 902, "throughput_tps": 117, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "Venice", "tag": "venice/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 198000, "max_completion_tokens": 32000, "max_prompt_tokens": null, "latency_ms": 1426, "throughput_tps": 66, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2032, "throughput_tps": 44, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.0, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 2675, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.86043265875784, "prompt_per_m": 1.0, "completion_per_m": 3.1999999999999997, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-5", "provider_name": "Venice", "tag": "venice/turbo", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 200000, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 4653, "throughput_tps": 25, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 1.2, "completion_per_m": 4.0, "input_cache_read_per_m": 0.24, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "anthropic/claude-opus-4.6", "provider_name": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1078, "throughput_tps": 32, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.6", "provider_name": "Azure", "tag": "azure/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 3826, "throughput_tps": 24, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.6", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2563, "throughput_tps": 44, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.6", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1964, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.6", "provider_name": "Anthropic", "tag": "anthropic", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 2411.5, "throughput_tps": 31, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 5.0, "completion_per_m": 25.0, "input_cache_read_per_m": 0.5, "input_cache_write_per_m": 6.25, "input_cache_write_1h_per_m": 10.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "anthropic/claude-opus-4.6", "provider_name": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1000000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 5.5, "completion_per_m": 27.5, "input_cache_read_per_m": 0.55, "input_cache_write_per_m": 6.875, "input_cache_write_1h_per_m": 11.0, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "qwen/qwen3-coder-next", "provider_name": "Parasail", "tag": "parasail/bf16", "quantization": "bf16", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 631.5, "throughput_tps": 61, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.12, "completion_per_m": 0.7999999999999999, "input_cache_read_per_m": 0.07, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "stepfun/step-3.5-flash", "provider_name": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1054, "throughput_tps": 67, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.61489088575097, "prompt_per_m": 0.09999999999999999, "completion_per_m": 0.3, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.5", "provider_name": "AtlasCloud", "tag": "atlas-cloud/int4", "quantization": "int4", "service_tier": null, "status": -2, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 709, "throughput_tps": 39, "uptime_5m_pct": 100, "uptime_30m_pct": 93.33333333333333, "uptime_1d_pct": 97.15335169880625, "prompt_per_m": 0.49, "completion_per_m": 2.5, "input_cache_read_per_m": 0.19999999999999998, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.5", "provider_name": "SiliconFlow", "tag": "siliconflow/int4", "quantization": "int4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 1587.5, "throughput_tps": 23, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 2.5, "input_cache_read_per_m": 0.15, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.5", "provider_name": "Venice", "tag": "venice", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 256000, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 860.5, "throughput_tps": 42, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.93031358885017, "prompt_per_m": 0.532, "completion_per_m": 3.3249999999999997, "input_cache_read_per_m": 0.20900000000000002, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.5", "provider_name": "Novita", "tag": "novita", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 2315.5, "throughput_tps": 34, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.49604031677465, "prompt_per_m": 0.5700000000000001, "completion_per_m": 2.8499999999999996, "input_cache_read_per_m": 0.095, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "moonshotai/kimi-k2.5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-2", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 976, "throughput_tps": 88, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 3.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "upstage/solar-pro-3", "provider_name": "Upstage", "tag": "upstage", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 223.5, "throughput_tps": 123, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.15, "completion_per_m": 0.6, "input_cache_read_per_m": 0.015, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2-her", "provider_name": "Minimax", "tag": "minimax", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 65536, "max_completion_tokens": 2048, "max_prompt_tokens": null, "latency_ms": 614, "throughput_tps": 47, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 90.73614557485526, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "writer/palmyra-x5", "provider_name": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1040000, "max_completion_tokens": 8192, "max_prompt_tokens": null, "latency_ms": 356, "throughput_tps": 69.5, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 6.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-audio", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 598, "throughput_tps": 100, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 2.5, "completion_per_m": 10.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "audio_usd": 3.2e-05, "audio_output_usd": 6.4e-05}, {"model_id": "openai/gpt-audio-mini", "provider_name": "OpenAI", "tag": "openai", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 464, "throughput_tps": 136, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 2.4, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "audio_usd": 6e-07, "audio_output_usd": 2.4e-06}, {"model_id": "z-ai/glm-4.7-flash", "provider_name": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 335, "throughput_tps": 48, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.060500000000000005, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7-flash", "provider_name": "Novita", "tag": "novita/bf16", "quantization": "bf16", "service_tier": null, "status": -5, "context_length": 200000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": 1530, "throughput_tps": 50, "uptime_5m_pct": 0, "uptime_30m_pct": 3.3333333333333335, "uptime_1d_pct": 2.5069637883008355, "prompt_per_m": 0.07, "completion_per_m": 0.39999999999999997, "input_cache_read_per_m": 0.01, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-5.2-codex", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 400000, "max_completion_tokens": 128000, "max_prompt_tokens": 272000, "latency_ms": 2093.5, "throughput_tps": 43, "uptime_5m_pct": null, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 1.75, "completion_per_m": 14.0, "input_cache_read_per_m": 0.175, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}, {"model_id": "bytedance-seed/seed-1.6-flash", "provider_name": "Seed", "tag": "seed/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 800.5, "throughput_tps": 87, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.075, "completion_per_m": 0.3, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "bytedance-seed/seed-1.6", "provider_name": "Seed", "tag": "seed/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 689.5, "throughput_tps": 38, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.25, "completion_per_m": 2.0, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.1", "provider_name": "Minimax", "tag": "minimax", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1254, "throughput_tps": 26, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 1.2, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "minimax/minimax-m2.1", "provider_name": "Minimax", "tag": "minimax/highspeed", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1445.5, "throughput_tps": 24, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 100, "prompt_per_m": 0.3, "completion_per_m": 2.4, "input_cache_read_per_m": 0.03, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "DeepInfra", "tag": "deepinfra/fp4/flex", "quantization": "fp4", "service_tier": "flex", "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1054, "throughput_tps": 52, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 0.32, "completion_per_m": 1.4, "input_cache_read_per_m": 0.064, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 1270, "throughput_tps": 26.5, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.9215070643642, "prompt_per_m": 0.39999999999999997, "completion_per_m": 1.75, "input_cache_read_per_m": 0.08, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "Venice", "tag": "venice/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 198000, "max_completion_tokens": 16384, "max_prompt_tokens": null, "latency_ms": 1846, "throughput_tps": 29, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 90.06514657980456, "prompt_per_m": 0.40040000000000003, "completion_per_m": 1.9292, "input_cache_read_per_m": 0.08008, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "Novita", "tag": "novita/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 204800, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 4695, "throughput_tps": 23, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.54, "completion_per_m": 1.9800000000000002, "input_cache_read_per_m": 0.099, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "Google", "tag": "google-vertex", "quantization": "unknown", "service_tier": null, "status": -5, "context_length": 200000, "max_completion_tokens": 128000, "max_prompt_tokens": null, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 0, "prompt_per_m": 0.6, "completion_per_m": 2.2, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "Z.AI", "tag": "z-ai/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 202752, "max_completion_tokens": 131072, "max_prompt_tokens": null, "latency_ms": 4101.5, "throughput_tps": 24, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.6, "completion_per_m": 2.2, "input_cache_read_per_m": 0.11, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "z-ai/glm-4.7", "provider_name": "Mancer 2", "tag": "mancer/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 131072, "max_completion_tokens": 117964, "max_prompt_tokens": null, "latency_ms": 1165, "throughput_tps": 36, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": 70.29702970297029, "prompt_per_m": 0.7, "completion_per_m": 2.5, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "google/gemini-3-flash-preview", "provider_name": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "service_tier": "flex", "status": -5, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 13062.5, "throughput_tps": 23, "uptime_5m_pct": null, "uptime_30m_pct": 0, "uptime_1d_pct": 23.745819397993312, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.5, "web_search_usd": 0.014, "image_usd": 2.5e-07, "audio_usd": 5e-07}, {"model_id": "google/gemini-3-flash-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "service_tier": "flex", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1824, "throughput_tps": 86, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.58304378040306, "prompt_per_m": 0.25, "completion_per_m": 1.5, "input_cache_read_per_m": 0.024999999999999998, "input_cache_write_per_m": 0.0416666666666667, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 1.5, "web_search_usd": 0.014, "image_usd": 2.5e-07, "audio_usd": 5e-07}, {"model_id": "google/gemini-3-flash-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1624.5, "throughput_tps": 81, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.72222222222223, "prompt_per_m": 0.5, "completion_per_m": 3.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.0, "web_search_usd": 0.014, "image_usd": 5e-07, "audio_usd": 1e-06}, {"model_id": "google/gemini-3-flash-preview", "provider_name": "Google", "tag": "google-vertex/global", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1099, "throughput_tps": 121, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 100, "prompt_per_m": 0.5, "completion_per_m": 3.0, "input_cache_read_per_m": 0.049999999999999996, "input_cache_write_per_m": 0.0833333333333333, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 3.0, "web_search_usd": 0.014, "image_usd": 5e-07, "audio_usd": 1e-06}, {"model_id": "google/gemini-3-flash-preview", "provider_name": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1464, "throughput_tps": 173, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.65753424657534, "prompt_per_m": 0.8999999999999999, "completion_per_m": 5.4, "input_cache_read_per_m": 0.09, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 5.4, "web_search_usd": 0.014, "image_usd": 9e-07, "audio_usd": 1.8e-06}, {"model_id": "google/gemini-3-flash-preview", "provider_name": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "service_tier": "priority", "status": 0, "context_length": 1048576, "max_completion_tokens": 65536, "max_prompt_tokens": null, "latency_ms": 1429.5, "throughput_tps": 119, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.77324263038548, "prompt_per_m": 0.8999999999999999, "completion_per_m": 5.4, "input_cache_read_per_m": 0.09, "input_cache_write_per_m": 0.15, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": 5.4, "web_search_usd": 0.014, "image_usd": 9e-07, "audio_usd": 1.8e-06}, {"model_id": "nvidia/nemotron-3-nano-30b-a3b", "provider_name": "Novita", "tag": "novita/fp4", "quantization": "fp4", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 32768, "max_prompt_tokens": null, "latency_ms": 357, "throughput_tps": 234, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 98.5373364126251, "prompt_per_m": 0.049999999999999996, "completion_per_m": 0.19999999999999998, "input_cache_read_per_m": null, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "nvidia/nemotron-3-nano-30b-a3b", "provider_name": "Nebius", "tag": "nebius/fp8", "quantization": "fp8", "service_tier": null, "status": 0, "context_length": 262144, "max_completion_tokens": 235929, "max_prompt_tokens": null, "latency_ms": 437, "throughput_tps": 191, "uptime_5m_pct": 100, "uptime_30m_pct": 100, "uptime_1d_pct": 99.29851909586905, "prompt_per_m": 0.06, "completion_per_m": 0.24, "input_cache_read_per_m": 0.012, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null}, {"model_id": "openai/gpt-5.2-chat", "provider_name": "Azure", "tag": "azure", "quantization": "unknown", "service_tier": null, "status": 0, "context_length": 128000, "max_completion_tokens": 32000, "max_prompt_tokens": 96000, "latency_ms": null, "throughput_tps": null, "uptime_5m_pct": null, "uptime_30m_pct": null, "uptime_1d_pct": null, "prompt_per_m": 1.75, "completion_per_m": 14.0, "input_cache_read_per_m": 0.175, "input_cache_write_per_m": null, "input_cache_write_1h_per_m": null, "internal_reasoning_per_m": null, "web_search_usd": 0.01}]}