diff --git "a/data/providers.json" "b/data/providers.json" --- "a/data/providers.json" +++ "b/data/providers.json" @@ -253,7 +253,8 @@ "hf_private": false, "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "bge-multilingual-gemma2" + "canonical_id": "bge-multilingual-gemma2", + "size_source": "hf-total" }, { "name": "All MiniLM L12 v2", @@ -807,1081 +808,5584 @@ "region": "Global", "gdpr_compliant": true, "eu_endpoints": true, - "models": [], - "lastUpdated": "2026-03-02T04:53:24.807Z" - }, - { - "name": "Nebius", - "url": "https://nebius.ai/services/token-factory/pricing", - "headquarters": "Netherlands", - "region": "EU", - "gdpr_compliant": true, - "eu_endpoints": true, "models": [ { - "name": "gpt-oss-120b (base)", + "name": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "type": "chat", - "input_price_per_1m": 0.15, - "output_price_per_1m": 0.6, + "input_price_per_1m": 0.02, + "output_price_per_1m": 0.05, + "currency": "USD", + "context_window": 131072, + "size_b": 8, + "canonical_id": "meta-llama-3-1-8b-turbo", + "hf_private": false + }, + { + "name": "deepinfra/Qwen/Qwen3.5-2B", + "type": "vision", + "input_price_per_1m": 0.02, + "output_price_per_1m": 0.1, "currency": "USD", - "size_b": 120, - "flavor": "base", "capabilities": [ - "tools", + "vision", "reasoning" ], - "hf_id": "openai/gpt-oss-120b", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "gpt-oss-120b-(base)" + "context_window": 262144, + "size_b": 2, + "canonical_id": "qwen3-5-2b", + "hf_private": false }, { - "name": "gpt-oss-20b (base)", - "type": "chat", - "input_price_per_1m": 0.05, + "name": "openai/gpt-5-nano", + "type": "vision", + "input_price_per_1m": 0.025, "output_price_per_1m": 0.2, "currency": "USD", - "size_b": 20, - "flavor": "base", "capabilities": [ - "tools", + "vision", "reasoning" ], - "hf_id": "openai/gpt-oss-20b", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "gpt-oss-20b-(base)" + "context_window": 400000, + "canonical_id": "gpt-5-nano" }, { - "name": "Kimi-K2-Instruct (base)", + "name": "novita/meta-llama/llama-3.2-3b-instruct", "type": "chat", - "input_price_per_1m": 0.5, - "output_price_per_1m": 2.4, + "input_price_per_1m": 0.03, + "output_price_per_1m": 0.05, + "currency": "USD", + "context_window": 32768, + "size_b": 3, + "canonical_id": "llama-3-2-3b", + "hf_id": "meta-llama/Llama-3.2-3B-Instruct", + "hf_private": false + }, + { + "name": "novita/meta-llama/llama-3-8b-instruct", + "type": "chat", + "input_price_per_1m": 0.04, + "output_price_per_1m": 0.04, "currency": "USD", - "flavor": "base", + "context_window": 8192, + "size_b": 8, + "canonical_id": "llama-3-8b", + "hf_id": "meta-llama/Meta-Llama-3-8B-Instruct", "capabilities": [ "tools" ], - "hf_id": "moonshotai/Kimi-K2-Instruct", - "size_b": 1026.5, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "kimi-k2-(base)" + "hf_private": false }, { - "name": "Qwen3-Coder-480B-A35B-Instruct (base)", + "name": "novita/meta-llama/llama-3.1-8b-instruct", "type": "chat", - "input_price_per_1m": 0.4, - "output_price_per_1m": 1.8, + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.05, "currency": "USD", - "size_b": 480, - "flavor": "base", + "context_window": 16384, + "size_b": 8, + "canonical_id": "llama-3-1-8b", + "hf_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "capabilities": [ "tools" ], - "hf_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-coder-480b-a35b-(base)" + "hf_private": false }, { - "name": "Qwen3-235B-A22B-Thinking-2507 (base)", + "name": "novita/sao10k/l3-8b-lunaris", "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 0.8, + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.05, + "currency": "USD", + "context_window": 8192, + "size_b": 8, + "canonical_id": "l3-8b-lunaris", + "hf_private": false + }, + { + "name": "novita/Sao10K/L3-8B-Stheno-v3.2", + "type": "chat", + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.05, + "currency": "USD", + "context_window": 8192, + "size_b": 8, + "canonical_id": "l3-8b-stheno-2", + "hf_private": false + }, + { + "name": "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B", + "type": "chat", + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.2, "currency": "USD", - "size_b": 235, - "flavor": "base", "capabilities": [ - "tools", "reasoning" ], - "hf_id": "Qwen/Qwen3-235B-A22B-Thinking-2507", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-235b-a22b-(base)" + "context_window": 262144, + "size_b": 30, + "canonical_id": "nemotron-3-nano-30b-a3b", + "hf_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", + "hf_private": false }, { - "name": "Qwen3-235B-A22B-Instruct-2507 (base)", + "name": "alibaba/qwen-turbo", "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 0.6, + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.2, + "currency": "USD", + "context_window": 1000000, + "canonical_id": "qwen-turbo" + }, + { + "name": "openai-responses/gpt-5-nano", + "type": "vision", + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 235, - "flavor": "base", "capabilities": [ - "tools", + "vision", "reasoning" ], - "hf_id": "Qwen/Qwen3-235B-A22B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-235b-a22b-(base)" + "context_window": 400000, + "canonical_id": "gpt-5-nano" }, { - "name": "Qwen3-30B-A3B-Thinking-2507 (base)", + "name": "azure/gpt-5-nano", "type": "chat", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.3, + "input_price_per_1m": 0.05, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 30, - "flavor": "base", "capabilities": [ - "tools", "reasoning" ], - "hf_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-30b-a3b-(base)" + "context_window": 200000, + "canonical_id": "gpt-5-nano" }, { - "name": "Qwen3-30B-A3B-Instruct-2507 (base)", + "name": "nebius/nvidia/nemotron-3-nano-omni", "type": "chat", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.3, + "input_price_per_1m": 0.06, + "output_price_per_1m": 0.24, "currency": "USD", - "size_b": 30, - "flavor": "base", "capabilities": [ - "tools" + "reasoning" ], - "hf_id": "Qwen/Qwen3-30B-A3B-Instruct-2507", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-30b-a3b-(base)" + "context_window": 300000, + "canonical_id": "nemotron-3-nano-omni" }, { - "name": "Qwen3-Coder-30B-A3B-Instruct (base)", + "name": "novita/baichuan/baichuan-m2-32b", "type": "chat", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.3, + "input_price_per_1m": 0.07, + "output_price_per_1m": 0.07, "currency": "USD", - "size_b": 30, - "flavor": "base", - "capabilities": [ - "tools" - ], - "hf_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-coder-30b-a3b-(base)" + "context_window": 131072, + "size_b": 32, + "canonical_id": "baichuan-m2-32b", + "hf_private": false }, { - "name": "Qwen3-30B-A3B (base)", + "name": "fireworks/gpt-oss-20b", "type": "chat", - "input_price_per_1m": 0.1, + "input_price_per_1m": 0.07, "output_price_per_1m": 0.3, "currency": "USD", - "size_b": 30, - "flavor": "base", "capabilities": [ - "tools", "reasoning" ], - "hf_id": "Qwen/Qwen3-30B-A3B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-30b-a3b-(base)" + "context_window": 131072, + "size_b": 20, + "canonical_id": "gpt-oss-20b", + "hf_id": "openai/gpt-oss-20b", + "hf_private": false }, { - "name": "Qwen3-32B (fast)", + "name": "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct", "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 0.6, + "input_price_per_1m": 0.07, + "output_price_per_1m": 0.16, "currency": "USD", + "context_window": 16384, "size_b": 32, - "flavor": "fast", - "capabilities": [ - "tools", - "reasoning" - ], - "hf_id": "Qwen/Qwen3-32B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-32b-(fast)" + "canonical_id": "qwen2-5-coder-32b", + "hf_private": false }, { - "name": "Qwen3-32B (base)", + "name": "deepinfra/microsoft/phi-4", "type": "chat", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.3, + "input_price_per_1m": 0.07, + "output_price_per_1m": 0.14, + "currency": "USD", + "context_window": 16384, + "canonical_id": "phi-4", + "size_b": 14, + "size_source": "manual", + "hf_id": "microsoft/phi-4", + "hf_private": false + }, + { + "name": "deepinfra/google/gemma-4-26B-A4B-it", + "type": "vision", + "input_price_per_1m": 0.07, + "output_price_per_1m": 0.34, "currency": "USD", - "size_b": 32, - "flavor": "base", "capabilities": [ - "tools", + "vision", "reasoning" ], - "hf_id": "Qwen/Qwen3-32B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-32b-(base)" + "context_window": 262144, + "size_b": 26, + "canonical_id": "gemma-4-26b-a4b", + "hf_id": "google/gemma-4-26B-A4B-it", + "hf_private": false }, { - "name": "Qwen3-14B (base)", + "name": "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "type": "chat", - "input_price_per_1m": 0.08, - "output_price_per_1m": 0.24, + "input_price_per_1m": 0.071, + "output_price_per_1m": 0.1, "currency": "USD", - "size_b": 14, - "flavor": "base", + "context_window": 262144, + "size_b": 235, + "canonical_id": "qwen3-235b-a22b", + "hf_id": "Qwen/Qwen3-235B-A22B", "capabilities": [ "tools", "reasoning" ], - "hf_id": "Qwen/Qwen3-14B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-14b-(base)" + "hf_private": false }, { - "name": "Qwen2.5-Coder-7B (base)", + "name": "novita/gryphe/mythomax-l2-13b", "type": "chat", - "input_price_per_1m": 0.03, + "input_price_per_1m": 0.09, "output_price_per_1m": 0.09, "currency": "USD", - "size_b": 7, - "flavor": "base", - "hf_private": false, - "canonical_id": "qwen2-5-coder-7b-(base)" + "context_window": 4096, + "size_b": 13, + "canonical_id": "mythomax-l2-13b", + "hf_id": "Gryphe/MythoMax-L2-13b", + "hf_private": false }, { - "name": "Qwen2.5-72B-Instruct (base)", + "name": "novita/inclusionai/ling-2.6-flash", "type": "chat", - "input_price_per_1m": 0.13, - "output_price_per_1m": 0.4, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "size_b": 72, - "flavor": "base", - "hf_private": false, - "canonical_id": "qwen2-5-72b-(base)" + "context_window": 262144, + "canonical_id": "ling-2-6-flash", + "capabilities": [ + "tools" + ] }, { - "name": "QwQ-32B (fast)", + "name": "novita/xiaomimimo/mimo-v2-flash", "type": "chat", - "input_price_per_1m": 0.5, - "output_price_per_1m": 1.5, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "size_b": 32, - "flavor": "fast", "capabilities": [ - "tools", "reasoning" ], - "hf_id": "Qwen/QwQ-32B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwq-32b-(fast)" + "context_window": 262144, + "canonical_id": "mimo-flash" }, { - "name": "QwQ-32B (base)", - "type": "chat", - "input_price_per_1m": 0.15, - "output_price_per_1m": 0.45, + "name": "google/gemini-2.5-flash-lite", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 32, - "flavor": "base", "capabilities": [ - "tools", + "vision", "reasoning" ], - "hf_id": "Qwen/QwQ-32B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwq-32b-(base)" + "context_window": 1048576, + "canonical_id": "gemini-2-5-flash-lite", + "hf_private": true }, { - "name": "GLM-4.5 (base)", - "type": "chat", - "input_price_per_1m": 0.6, - "output_price_per_1m": 2.2, + "name": "openai/gpt-4.1-nano", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "flavor": "base", "capabilities": [ - "tools", - "reasoning" + "vision" ], - "hf_id": "zai-org/GLM-4.5", - "size_b": 358.3, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "glm-4-5-(base)" + "context_window": 1047576, + "canonical_id": "gpt-4-1-nano" }, { - "name": "GLM-4.5-Air (base)", + "name": "groq/openai/gpt-oss-20b", "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 1.2, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.5, "currency": "USD", - "flavor": "base", + "context_window": 131072, + "size_b": 20, + "canonical_id": "gpt-oss-20b", + "hf_id": "openai/gpt-oss-20b", "capabilities": [ "tools", "reasoning" ], - "hf_id": "zai-org/GLM-4.5-Air", - "size_b": 110.5, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "glm-4-5-air-(base)" + "hf_private": false }, { - "name": "DeepSeek-R1-0528 (fast)", + "name": "nebius/qwen/qwen3-30b-a3b-instruct-2507", "type": "chat", - "input_price_per_1m": 2, - "output_price_per_1m": 6, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "flavor": "fast", "capabilities": [ - "tools", "reasoning" ], - "hf_id": "deepseek-ai/DeepSeek-R1-0528", - "size_b": 684.5, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "deepseek-r1-(fast)" + "context_window": 128000, + "size_b": 30, + "canonical_id": "qwen3-30b-a3b", + "hf_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", + "hf_private": false }, { - "name": "DeepSeek-R1-0528 (base)", + "name": "nebius/google/gemma-3-27b-it", "type": "chat", - "input_price_per_1m": 0.8, - "output_price_per_1m": 2.4, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "flavor": "base", "capabilities": [ - "tools", "reasoning" ], - "hf_id": "deepseek-ai/DeepSeek-R1-0528", - "size_b": 684.5, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "deepseek-r1-(base)" + "context_window": 128000, + "size_b": 27, + "canonical_id": "gemma-3-27b", + "hf_id": "google/gemma-3-27b-it", + "hf_private": false }, { - "name": "DeepSeek-V3-0324 (fast)", + "name": "nebius/qwen/qwen3-32b", "type": "chat", - "input_price_per_1m": 0.75, - "output_price_per_1m": 2.25, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "flavor": "fast", - "size_b": 671, - "hf_id": "deepseek-ai/DeepSeek-V3", - "size_source": "manual", - "hf_private": false, "capabilities": [ - "tools" + "reasoning" ], - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "deepseek-(fast)" + "context_window": 128000, + "size_b": 32, + "canonical_id": "qwen3-32b", + "hf_id": "Qwen/Qwen3-32B", + "hf_private": false }, { - "name": "DeepSeek-V3-0324 (base)", + "name": "deepinfra/Qwen/Qwen3-32B", "type": "chat", - "input_price_per_1m": 0.5, - "output_price_per_1m": 1.5, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "flavor": "base", - "hf_id": "deepseek-ai/DeepSeek-V3", - "size_b": 671, - "size_source": "manual", - "hf_private": false, + "context_window": 40000, + "size_b": 32, + "canonical_id": "qwen3-32b", + "hf_id": "Qwen/Qwen3-32B", "capabilities": [ - "tools" + "tools", + "reasoning" ], - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "deepseek-(base)" + "hf_private": false }, { - "name": "DeepSeek-V3 (base)", + "name": "deepinfra/deepseek-ai/DeepSeek-V4-Flash", "type": "chat", - "input_price_per_1m": 0.5, - "output_price_per_1m": 1.5, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.2, "currency": "USD", - "flavor": "base", - "hf_id": "deepseek-ai/DeepSeek-V3", - "size_b": 671, - "size_source": "manual", - "hf_private": false, "capabilities": [ - "tools" + "reasoning" ], - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "deepseek-(base)" + "context_window": 1048576, + "canonical_id": "deepseek-flash", + "size_b": 158.1, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Flash", + "hf_private": false }, { - "name": "Llama-3.3-70B-Instruct (fast)", - "type": "chat", - "input_price_per_1m": 0.25, - "output_price_per_1m": 0.75, + "name": "deepinfra/ByteDance/Seed-2.0-mini", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 70, - "flavor": "fast", "capabilities": [ - "tools" + "vision", + "reasoning" ], - "hf_private": false, - "canonical_id": "llama-3-3-70b-(fast)" + "context_window": 256000, + "canonical_id": "seed-2-0-mini" }, { - "name": "Llama-3.3-70B-Instruct (base)", + "name": "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B", "type": "chat", - "input_price_per_1m": 0.13, - "output_price_per_1m": 0.4, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.5, "currency": "USD", - "size_b": 70, - "flavor": "base", "capabilities": [ - "tools" + "reasoning" ], - "hf_private": false, - "canonical_id": "llama-3-3-70b-(base)" + "context_window": 262144, + "size_b": 120, + "canonical_id": "nvidia-nemotron-3-super-120b-a12b", + "hf_private": false }, { - "name": "Llama-3.1-8B-Instruct (fast)", + "name": "doubleword/deepseek-v4-flash", "type": "chat", - "input_price_per_1m": 0.03, - "output_price_per_1m": 0.09, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.2, "currency": "USD", - "size_b": 8, - "flavor": "fast", "capabilities": [ - "tools" + "reasoning" ], - "hf_private": false, - "canonical_id": "llama-3-1-8b-(fast)" + "context_window": 1048576, + "canonical_id": "deepseek-flash", + "size_b": 158.1, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Flash", + "hf_private": false }, { - "name": "Llama-3.1-8B-Instruct (base)", - "type": "chat", - "input_price_per_1m": 0.02, - "output_price_per_1m": 0.06, + "name": "vertex/gemini-2.5-flash-lite", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 8, - "flavor": "base", "capabilities": [ - "tools" + "vision", + "reasoning" ], - "hf_private": false, - "canonical_id": "llama-3-1-8b-(base)" + "context_window": 1048576, + "canonical_id": "gemini-2-5-flash-lite", + "hf_private": true }, { - "name": "Llama-3.1-405B-Instruct (base)", - "type": "chat", - "input_price_per_1m": 1, - "output_price_per_1m": 3, + "name": "openai-responses/gpt-4.1-nano", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 405, - "flavor": "base", - "hf_private": false, - "canonical_id": "llama-3-1-405b-(base)" + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1-nano" }, { - "name": "Llama-3_1-Nemotron-Ultra-253B-v1 (base)", + "name": "mistral/mistral-small-2503", "type": "chat", - "input_price_per_1m": 0.6, - "output_price_per_1m": 1.8, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "size_b": 253, - "flavor": "base", + "context_window": 32768, + "canonical_id": "mistral-small", + "size_b": 119, + "hf_id": "mistralai/Mistral-Small-4-119B-2603", "capabilities": [ + "vision", + "tools", "reasoning" ], - "hf_id": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "llama-3-1-nemotron-ultra-253b-(base)" + "hf_private": false }, { - "name": "Gemma-2-2b-it (base)", + "name": "mistral/devstral-small-latest", "type": "chat", - "input_price_per_1m": 0.02, - "output_price_per_1m": 0.06, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "size_b": 2, - "flavor": "base", - "hf_private": false, - "canonical_id": "gemma-2-2b-(base)" + "context_window": 131072, + "canonical_id": "devstral-small" }, { - "name": "Gemma-2-9b-it (base)", + "name": "mistral/devstral-small-2507", "type": "chat", - "input_price_per_1m": 0.03, - "output_price_per_1m": 0.09, + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, "currency": "USD", - "size_b": 9, - "flavor": "base", - "hf_private": false, - "canonical_id": "gemma-2-9b-(base)" + "context_window": 131072, + "canonical_id": "devstral-small" }, { - "name": "Devstral-Small-2505 (base)", - "type": "chat", - "input_price_per_1m": 0.08, - "output_price_per_1m": 0.24, + "name": "azure/openai-responses/gpt-4.1-nano", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "flavor": "base", "capabilities": [ - "tools" + "vision" ], - "hf_id": "mistralai/Devstral-Small-2507", - "size_b": 24, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "devstral-small-(base)" + "context_window": 1047576, + "canonical_id": "gpt-4-1-nano" }, { - "name": "Hermes-4-405B (base)", - "type": "chat", - "input_price_per_1m": 1, - "output_price_per_1m": 3, + "name": "azure/gpt-4.1-nano", + "type": "vision", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 405, - "flavor": "base", "capabilities": [ + "vision", "reasoning" ], - "hf_id": "NousResearch/Hermes-4-405B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "hermes-4-405b-(base)" + "context_window": 1047576, + "canonical_id": "gpt-4-1-nano" }, { - "name": "Hermes-4-70B (base)", + "name": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "type": "chat", - "input_price_per_1m": 0.13, - "output_price_per_1m": 0.4, + "input_price_per_1m": 0.12, + "output_price_per_1m": 0.3, "currency": "USD", + "context_window": 131072, "size_b": 70, - "flavor": "base", + "canonical_id": "llama-3-3-70b-turbo", + "hf_private": false + }, + { + "name": "openai/gpt-5-mini", + "type": "vision", + "input_price_per_1m": 0.125, + "output_price_per_1m": 1, + "currency": "USD", "capabilities": [ + "vision", "reasoning" ], - "hf_id": "NousResearch/Hermes-4-70B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "hermes-4-70b-(base)" + "context_window": 400000, + "canonical_id": "gpt-5-mini" }, { - "name": "Hermes-3-Llama-3.1-405B (base)", - "type": "chat", - "input_price_per_1m": 1, - "output_price_per_1m": 3, + "name": "novita/google/gemma-4-26b-a4b-it", + "type": "vision", + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.4, "currency": "USD", - "size_b": 405, - "flavor": "base", - "hf_private": false, - "hf_id": "NousResearch/Hermes-3-Llama-3.1-405B", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "hermes-3-llama-3-1-405b-(base)" + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 26, + "canonical_id": "gemma-4-26b-a4b", + "hf_id": "google/gemma-4-26B-A4B-it", + "hf_private": false }, { - "name": "gemma-3-27b-it", + "name": "parasail/google/gemma-4-26B-A4B-it", "type": "vision", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.3, + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.4, "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 26, + "canonical_id": "gemma-4-26b-a4b", + "hf_id": "google/gemma-4-26B-A4B-it", + "hf_private": false + }, + { + "name": "nebius/nousresearch/hermes-4-70b", + "type": "chat", + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "size_b": 70, + "canonical_id": "hermes-4-70b", + "hf_id": "NousResearch/Hermes-4-70B", + "hf_private": false + }, + { + "name": "nebius/meta-llama/Llama-3.3-70B-Instruct", + "type": "chat", + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.4, + "currency": "USD", + "context_window": 128000, + "size_b": 70, + "canonical_id": "llama-3-3-70b", + "hf_id": "meta-llama/Llama-3.3-70B-Instruct", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "deepinfra/google/gemma-4-31B-it", + "type": "vision", + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.38, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 31, + "canonical_id": "gemma-4-31b", + "hf_id": "google/gemma-4-31B-it", + "hf_private": false + }, + { + "name": "novita/deepseek/deepseek-v4-flash", + "type": "chat", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "deepseek-flash", + "size_b": 158.1, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Flash", + "hf_private": false + }, + { + "name": "parasail/parasail-deepseek-v4-flash", + "type": "chat", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "context_window": 1048576, + "canonical_id": "parasail-deepseek-flash" + }, + { + "name": "fireworks/deepseek-v4-flash", + "type": "chat", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "deepseek-flash", + "size_b": 158.1, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Flash", + "hf_private": false + }, + { + "name": "deepinfra/Qwen/Qwen3.5-35B-A3B", + "type": "vision", + "input_price_per_1m": 0.14, + "output_price_per_1m": 1, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 35, + "canonical_id": "qwen3-5-35b-a3b", + "hf_id": "Qwen/Qwen3.5-35B-A3B", + "hf_private": false + }, + { + "name": "xiaomi/mimo-v2.5", + "type": "vision", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "mimo-5", + "size_b": 310.8, + "size_source": "hf-total", + "hf_id": "XiaomiMiMo/MiMo-V2.5", + "hf_private": false + }, + { + "name": "deepseek/deepseek-chat", + "type": "chat", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "context_window": 1000000, + "canonical_id": "deepseek", + "size_b": 685, + "hf_id": "deepseek-ai/DeepSeek-V3-0324", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "deepseek/deepseek-v4-flash", + "type": "chat", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "context_window": 1000000, + "canonical_id": "deepseek-flash", + "size_b": 158.1, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Flash", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepseek/deepseek-reasoner", + "type": "chat", + "input_price_per_1m": 0.14, + "output_price_per_1m": 0.28, + "currency": "USD", + "context_window": 1000000, + "canonical_id": "deepseek-reasoner" + }, + { + "name": "novita/deepseek/deepseek-r1-distill-qwen-14b", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.15, + "currency": "USD", + "context_window": 128000, + "size_b": 14, + "canonical_id": "deepseek-r1-distill-qwen-14b", + "hf_private": false + }, + { + "name": "parasail/parasail-qwen3-235b-a22b-instruct-2507", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.85, + "currency": "USD", + "context_window": 262144, + "size_b": 235, + "canonical_id": "parasail-qwen3-235b-a22b", + "hf_private": false + }, + { + "name": "openai/gpt-4o-mini", + "type": "vision", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 128000, + "canonical_id": "gpt-4o-mini" + }, + { + "name": "groq/openai/gpt-oss-120b", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.75, + "currency": "USD", + "context_window": 131072, + "size_b": 120, + "canonical_id": "gpt-oss-120b", + "hf_id": "openai/gpt-oss-120b", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "nebius/qwen/qwen3-next-80b-a3b-thinking", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "size_b": 80, + "canonical_id": "qwen3-next-80b-a3b", + "hf_id": "Qwen/Qwen3-Next-80B-A3B-Instruct", + "hf_private": false + }, + { + "name": "nebius/openai/gpt-oss-120b", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 131000, + "size_b": 120, + "canonical_id": "gpt-oss-120b", + "hf_id": "openai/gpt-oss-120b", + "hf_private": false + }, + { + "name": "fireworks/gpt-oss-120b", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 131072, + "size_b": 120, + "canonical_id": "gpt-oss-120b", + "hf_id": "openai/gpt-oss-120b", + "hf_private": false + }, + { + "name": "deepinfra/MiniMaxAI/MiniMax-M2.5", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 1.15, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 196608, + "canonical_id": "minimax-m2-5", + "size_b": 228.7, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "hf_private": false + }, + { + "name": "tensorx/deepseek-v4-flash", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "deepseek-flash", + "size_b": 158.1, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Flash", + "hf_private": false + }, + { + "name": "mistral/mistral-small-2603", + "type": "vision", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "mistral-small", + "size_b": 119, + "hf_id": "mistralai/Mistral-Small-4-119B-2603", + "hf_private": false + }, + { + "name": "mistral/mistral-small-latest", + "type": "vision", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "mistral-small", + "size_b": 119, + "hf_id": "mistralai/Mistral-Small-4-119B-2603", + "hf_private": false + }, + { + "name": "azure/gpt-4o-mini", + "type": "vision", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 128000, + "canonical_id": "gpt-4o-mini" + }, + { + "name": "novita/mistralai/mistral-nemo", + "type": "chat", + "input_price_per_1m": 0.17, + "output_price_per_1m": 0.17, + "currency": "USD", + "context_window": 131072, + "canonical_id": "mistral-nemo", + "size_b": 12, + "hf_id": "mistralai/Mistral-Nemo-Instruct-2407", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.85, + "currency": "USD", + "context_window": 1048576, + "size_b": 17, + "canonical_id": "llama-4-maverick-17b-128e-fp8", + "hf_private": false + }, + { + "name": "novita/qwen/qwen3-235b-a22b-fp8", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.8, + "currency": "USD", + "context_window": 128000, + "size_b": 235, + "canonical_id": "qwen3-235b-a22b-fp8", + "hf_private": false + }, + { + "name": "openai/gpt-5.4-nano", + "type": "vision", + "input_price_per_1m": 0.2, + "output_price_per_1m": 1.25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-4-nano" + }, + { + "name": "nebius/qwen/qwen3-235b-a22b-instruct-2507", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.6, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "size_b": 235, + "canonical_id": "qwen3-235b-a22b", + "hf_id": "Qwen/Qwen3-235B-A22B", + "hf_private": false + }, + { + "name": "xai/grok-4-fast-non-reasoning", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.5, + "currency": "USD", + "context_window": 2000000, + "canonical_id": "grok-4-fast-non-reasoning", + "hf_private": true + }, + { + "name": "xai/grok-4-fast", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.5, + "currency": "USD", + "context_window": 2000000, + "canonical_id": "grok-4-fast", + "hf_private": true + }, + { + "name": "xai/grok-code-fast-1", + "type": "vision", + "input_price_per_1m": 0.2, + "output_price_per_1m": 1.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 256000, + "canonical_id": "grok-code-fast-1", + "hf_private": true + }, + { + "name": "xai/grok-4-1-fast-non-reasoning", + "type": "vision", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 2000000, + "canonical_id": "grok-4-1-fast-non-reasoning", + "hf_private": true + }, + { + "name": "xai/grok-4-1-fast-reasoning", + "type": "vision", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 2000000, + "canonical_id": "grok-4-1-fast-reasoning", + "hf_private": true + }, + { + "name": "deepinfra/Qwen/Qwen3-235B-A22B", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.6, + "currency": "USD", + "context_window": 40000, + "size_b": 235, + "canonical_id": "qwen3-235b-a22b", + "hf_id": "Qwen/Qwen3-235B-A22B", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepinfra/zai-org/GLM-4.5-Air", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 1.1, + "currency": "USD", + "context_window": 131072, + "canonical_id": "glm-4-5-air", + "size_b": 110.5, + "hf_id": "zai-org/GLM-4.5-Air", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "alibaba/qwen3-30b-a3b-instruct-2507", + "type": "vision", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.8, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 131072, + "size_b": 30, + "canonical_id": "qwen3-30b-a3b", + "hf_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", + "hf_private": false + }, + { + "name": "openai-responses/gpt-5.4-nano", + "type": "vision", + "input_price_per_1m": 0.2, + "output_price_per_1m": 1.25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-4-nano" + }, + { + "name": "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", + "type": "chat", + "input_price_per_1m": 0.23, + "output_price_per_1m": 2.3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 262144, + "size_b": 235, + "canonical_id": "qwen3-235b-a22b", + "hf_id": "Qwen/Qwen3-235B-A22B", + "hf_private": false + }, + { + "name": "deepinfra/meta-llama/Llama-3.3-70B-Instruct", + "type": "chat", + "input_price_per_1m": 0.23, + "output_price_per_1m": 0.4, + "currency": "USD", + "context_window": 131072, + "size_b": 70, + "canonical_id": "llama-3-3-70b", + "hf_id": "meta-llama/Llama-3.3-70B-Instruct", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "deepinfra/Qwen/Qwen2.5-72B-Instruct", + "type": "chat", + "input_price_per_1m": 0.23, + "output_price_per_1m": 0.4, + "currency": "USD", + "context_window": 131072, + "size_b": 72, + "canonical_id": "qwen2-5-72b", + "hf_private": false + }, + { + "name": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "type": "chat", + "input_price_per_1m": 0.23, + "output_price_per_1m": 0.69, + "currency": "USD", + "context_window": 64000, + "size_b": 70, + "canonical_id": "deepseek-r1-distill-llama-70b", + "hf_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "capabilities": [ + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct", + "type": "chat", + "input_price_per_1m": 0.23, + "output_price_per_1m": 0.4, + "currency": "USD", + "context_window": 130815, + "size_b": 70, + "canonical_id": "meta-llama-3-1-70b", + "hf_private": false + }, + { + "name": "google/gemini-3.1-flash-lite-preview", + "type": "vision", + "input_price_per_1m": 0.25, + "output_price_per_1m": 1.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-1-flash-lite", + "hf_private": true + }, + { + "name": "deepinfra/ByteDance/Seed-1.8", + "type": "vision", + "input_price_per_1m": 0.25, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "seed-1-8" + }, + { + "name": "vertex/gemini-3-flash-preview", + "type": "vision", + "input_price_per_1m": 0.25, + "output_price_per_1m": 1.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-flash", + "hf_private": true + }, + { + "name": "vertex/gemini-3.1-flash-lite", + "type": "vision", + "input_price_per_1m": 0.25, + "output_price_per_1m": 1.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-1-flash-lite", + "hf_private": true + }, + { + "name": "vertex/gemini-3.1-flash-lite-preview", + "type": "vision", + "input_price_per_1m": 0.25, + "output_price_per_1m": 1.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-1-flash-lite", + "hf_private": true + }, + { + "name": "openai-responses/gpt-5-mini", + "type": "vision", + "input_price_per_1m": 0.25, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-mini" + }, + { + "name": "mistral/open-mistral-7b", + "type": "chat", + "input_price_per_1m": 0.25, + "output_price_per_1m": 0.25, + "currency": "USD", + "context_window": 32768, + "size_b": 7, + "canonical_id": "open-mistral-7b", + "hf_private": false + }, + { + "name": "azure/gpt-5-mini", + "type": "chat", + "input_price_per_1m": 0.25, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "gpt-5-mini" + }, + { + "name": "deepinfra/Qwen/Qwen3.5-27B", + "type": "vision", + "input_price_per_1m": 0.26, + "output_price_per_1m": 2.6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 27, + "canonical_id": "qwen3-5-27b", + "hf_id": "Qwen/Qwen3.5-27B", + "hf_private": false + }, + { + "name": "novita/deepseek/deepseek-v3.2", + "type": "chat", + "input_price_per_1m": 0.269, + "output_price_per_1m": 0.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 163840, + "canonical_id": "deepseek-2", + "size_b": 30.8, + "hf_id": "deepseek-ai/DeepSeek-V3.2-Exp", + "hf_private": false + }, + { + "name": "inceptron/minimax-m2.5", + "type": "chat", + "input_price_per_1m": 0.28, + "output_price_per_1m": 1.1, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 196608, + "canonical_id": "minimax-m2-5", + "size_b": 228.7, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "hf_private": false + }, + { + "name": "novita/baidu/ernie-4.5-300b-a47b-paddle", + "type": "chat", + "input_price_per_1m": 0.28, + "output_price_per_1m": 1.1, + "currency": "USD", + "context_window": 123000, + "size_b": 300, + "canonical_id": "ernie-4-5-300b-a47b-paddle", + "hf_private": false + }, + { + "name": "novita/inclusionai/ring-2.6-1t", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 262144, + "canonical_id": "ring-2-6-1t" + }, + { + "name": "novita/minimax/minimax-m2.7", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "minimax-m2-7", + "size_b": 230, + "size_source": "manual", + "hf_id": "MiniMaxAI/MiniMax-M2.7", + "hf_private": false + }, + { + "name": "novita/inclusionai/ling-2.6-1t", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 2.5, + "currency": "USD", + "context_window": 262144, + "canonical_id": "ling-2-6-1t", + "capabilities": [ + "tools" + ] + }, + { + "name": "novita/kwaipilot/kat-coder-pro", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "context_window": 256000, + "canonical_id": "kat-coder-pro", + "capabilities": [ + "tools" + ] + }, + { + "name": "novita/deepseek/deepseek-r1-distill-qwen-32b", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.3, + "currency": "USD", + "context_window": 12800, + "size_b": 32, + "canonical_id": "deepseek-r1-distill-qwen-32b", + "hf_private": false + }, + { + "name": "google/gemini-2.5-flash", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-flash", + "hf_private": true + }, + { + "name": "parasail/parasail-gemma3-27b-it", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.5, + "currency": "USD", + "context_window": 128000, "size_b": 27, + "canonical_id": "parasail-gemma3-27b", + "hf_private": false + }, + { + "name": "nebius/deepseek-ai/DeepSeek-V3.2", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.45, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 164000, + "canonical_id": "deepseek-2", + "size_b": 30.8, + "hf_id": "deepseek-ai/DeepSeek-V3.2-Exp", + "hf_private": false + }, + { + "name": "nebius/minimaxi/minimax-m2.5", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "canonical_id": "minimax-m2-5", + "size_b": 228.7, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "hf_private": false + }, + { + "name": "nebius/nvidia/nemotron-3-super-120b-a12b", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.9, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "size_b": 120, + "canonical_id": "nemotron-3-super-120b-a12b", + "hf_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", + "hf_private": false + }, + { + "name": "fireworks/minimax-m3", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 512000, + "canonical_id": "minimax-m3", + "size_b": 427, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/Minimax-M3", + "hf_private": false + }, + { + "name": "fireworks/minimax-m2.5", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "context_window": 196608, + "canonical_id": "minimax-m2-5", + "size_b": 228.7, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "fireworks/minimax-m2.7", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "context_window": 196608, + "canonical_id": "minimax-m2-7", + "size_b": 230, + "size_source": "manual", + "hf_id": "MiniMaxAI/MiniMax-M2.7", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "coding/gemini-2.5-flash", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-flash", + "hf_private": true + }, + { + "name": "xai/grok-3-mini", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 131072, + "canonical_id": "grok-3-mini", + "hf_private": true + }, + { + "name": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1, + "currency": "USD", + "context_window": 262144, + "size_b": 480, + "canonical_id": "qwen3-coder-480b-a35b-turbo", + "hf_private": false + }, + { + "name": "deepinfra/deepseek-ai/DeepSeek-V3.1", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1, + "currency": "USD", + "context_window": 163840, + "canonical_id": "deepseek-1", + "size_b": 671, + "hf_id": "deepseek-ai/DeepSeek-V3.1", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "vertex/gemini-2.5-flash", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-flash", + "hf_private": true + }, + { + "name": "vertex/gemini-2.5-flash-image", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-flash-image", + "hf_private": true + }, + { + "name": "bedrock/minimax-m2.5", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "canonical_id": "minimax-m2-5", + "size_b": 228.7, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "hf_private": false + }, + { + "name": "alibaba/qwen3-coder-flash", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "qwen3-coder-flash" + }, + { + "name": "mistral/codestral-latest", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.9, + "currency": "USD", + "context_window": 131072, + "canonical_id": "codestral", + "capabilities": [ + "files", + "tools" + ] + }, + { + "name": "minimaxi/minimax-m3", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "minimax-m3", + "size_b": 427, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/Minimax-M3", + "hf_private": false + }, + { + "name": "minimaxi/MiniMax-M2.7", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "minimax-m2-7", + "size_b": 230, + "size_source": "manual", + "hf_id": "MiniMaxAI/MiniMax-M2.7", + "hf_private": false + }, + { + "name": "minimaxi/MiniMax-M2", + "type": "chat", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "context_window": 200000, + "canonical_id": "minimax-m2", + "size_b": 228.7, + "hf_id": "MiniMaxAI/MiniMax-M2", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "minimaxi/MiniMax-M2.5", + "type": "vision", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "minimax-m2-5", + "size_b": 228.7, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "hf_private": false + }, + { + "name": "alibaba/qwen3.7-plus", + "type": "vision", + "input_price_per_1m": 0.32, + "output_price_per_1m": 1.28, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "qwen3-7-plus" + }, + { + "name": "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct", + "type": "chat", + "input_price_per_1m": 0.35, + "output_price_per_1m": 0.4, + "currency": "USD", + "context_window": 131072, + "size_b": 90, + "canonical_id": "llama-3-2-90b", + "hf_private": false + }, + { + "name": "doubleword/nvidia-nemotron-3-ultra", + "type": "chat", + "input_price_per_1m": 0.37, + "output_price_per_1m": 1.87, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 262144, + "canonical_id": "nvidia-nemotron-3-ultra" + }, + { + "name": "novita/qwen/qwen-2.5-72b-instruct", + "type": "chat", + "input_price_per_1m": 0.38, + "output_price_per_1m": 0.4, + "currency": "USD", + "context_window": 32000, + "size_b": 72, + "canonical_id": "qwen-2-5-72b", + "hf_id": "Qwen/Qwen2.5-72B-Instruct", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "novita/meta-llama/llama-3.3-70b-instruct", + "type": "chat", + "input_price_per_1m": 0.39, + "output_price_per_1m": 0.39, + "currency": "USD", + "context_window": 131072, + "size_b": 70, + "canonical_id": "llama-3-3-70b", + "hf_id": "meta-llama/Llama-3.3-70B-Instruct", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "novita/deepseek/deepseek-v3-turbo", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.3, + "currency": "USD", + "context_window": 128000, + "canonical_id": "deepseek-turbo" + }, + { + "name": "novita/deepseek/deepseek-v3-0324", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.3, + "currency": "USD", + "context_window": 128000, + "canonical_id": "deepseek", + "size_b": 685, + "hf_id": "deepseek-ai/DeepSeek-V3-0324", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "openai/gpt-4.1-mini", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1-mini" + }, + { + "name": "fireworks/qwen3.7-plus", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 262144, + "canonical_id": "qwen3-7-plus" + }, + { + "name": "deepinfra/XiaomiMiMo/MiMo-V2.5", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "mimo-5", + "size_b": 310.8, + "size_source": "hf-total", + "hf_id": "XiaomiMiMo/MiMo-V2.5", + "hf_private": false + }, + { + "name": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.6, + "currency": "USD", + "context_window": 262144, + "size_b": 480, + "canonical_id": "qwen3-coder-480b-a35b", + "hf_private": false + }, + { + "name": "tensorx/minimax-m3", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "minimax-m3", + "size_b": 427, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/Minimax-M3", + "hf_private": false + }, + { + "name": "alibaba/qwen-plus", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.2, + "currency": "USD", + "context_window": 131072, + "canonical_id": "qwen-plus", + "capabilities": [ + "tools" + ] + }, + { + "name": "openai-responses/gpt-4.1-mini", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1-mini" + }, + { + "name": "mistral/mistral-medium-latest", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 2, + "currency": "USD", + "context_window": 131072, + "canonical_id": "mistral-medium" + }, + { + "name": "mistral/devstral-medium-2507", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 2, + "currency": "USD", + "context_window": 131072, + "canonical_id": "devstral-medium" + }, + { + "name": "mistral/devstral-latest", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 2, + "currency": "USD", + "context_window": 256000, + "canonical_id": "devstral", + "size_b": 123, + "size_source": "manual", + "hf_id": "mistralai/Devstral-2-123B-Instruct-2512", + "capabilities": [ + "files", + "tools" + ], + "hf_private": false + }, + { + "name": "azure/openai-responses/gpt-4.1-mini", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1-mini" + }, + { + "name": "azure/gpt-4.1-mini", + "type": "vision", + "input_price_per_1m": 0.4, + "output_price_per_1m": 1.6, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1-mini" + }, + { + "name": "xiaomi/mimo-v2.5-pro", + "type": "chat", + "input_price_per_1m": 0.435, + "output_price_per_1m": 0.87, + "currency": "USD", + "context_window": 1048576, + "canonical_id": "mimo-5-pro", + "size_b": 1023.2, + "size_source": "hf-total", + "hf_id": "XiaomiMiMo/MiMo-V2.5-Pro", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepseek/deepseek-v4-pro", + "type": "chat", + "input_price_per_1m": 0.435, + "output_price_per_1m": 0.87, + "currency": "USD", + "context_window": 1000000, + "canonical_id": "deepseek-pro", + "size_b": 861.6, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepinfra/Kimi K2.5", + "type": "vision", + "input_price_per_1m": 0.45, + "output_price_per_1m": 2.25, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 262100, + "canonical_id": "kimi-k2-5", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.5", + "hf_private": false + }, + { + "name": "sference/minimax-m3", + "type": "chat", + "input_price_per_1m": 0.45, + "output_price_per_1m": 1.8, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "minimax-m3", + "size_b": 427, + "size_source": "hf-total", + "hf_id": "MiniMaxAI/Minimax-M3", + "hf_private": false + }, + { + "name": "deepinfra/Qwen/Qwen3.5-397B-A17B", + "type": "vision", + "input_price_per_1m": 0.49, + "output_price_per_1m": 3.6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 397, + "canonical_id": "qwen3-5-397b-a17b", + "hf_id": "Qwen/Qwen3.5-397B-A17B", + "hf_private": false + }, + { + "name": "google/gemini-3.1-flash-image-preview", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 131072, + "canonical_id": "gemini-3-1-flash-image", + "hf_private": true + }, + { + "name": "google/gemini-3-flash-preview", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-flash", + "hf_private": true + }, + { + "name": "nebius/moonshotai/kimi-k2.5", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "kimi-k2-5", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.5", + "hf_private": false + }, + { + "name": "fireworks/qwen3.6-plus", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 131072, + "canonical_id": "qwen3-6-plus" + }, + { + "name": "deepinfra/ByteDance/Seed-2.0-pro", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "seed-2-0-pro" + }, + { + "name": "deepinfra/ByteDance/Seed-2.0-code", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "seed-2-0-code" + }, + { + "name": "vertex/gemini-3.1-flash-image-preview", + "type": "vision", + "input_price_per_1m": 0.5, + "output_price_per_1m": 2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 131072, + "canonical_id": "gemini-3-1-flash-image", + "hf_private": true + }, + { + "name": "alibaba/qwen3.6-plus", + "type": "chat", + "input_price_per_1m": 0.5, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "qwen3-6-plus" + }, + { + "name": "mistral/mistral-large-latest", + "type": "chat", + "input_price_per_1m": 0.5, + "output_price_per_1m": 1.5, + "currency": "USD", + "context_window": 131072, + "canonical_id": "mistral-large", + "capabilities": [ + "files", + "tools" + ] + }, + { + "name": "novita/meta-llama/llama-3-70b-instruct", + "type": "chat", + "input_price_per_1m": 0.51, + "output_price_per_1m": 0.74, + "currency": "USD", + "context_window": 8192, + "size_b": 70, + "canonical_id": "llama-3-70b", + "hf_private": false + }, + { + "name": "openai/o4-mini", + "type": "chat", + "input_price_per_1m": 0.55, + "output_price_per_1m": 2.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o4-mini" + }, + { + "name": "vertex/deepseek-v3.2", + "type": "vision", + "input_price_per_1m": 0.56, + "output_price_per_1m": 1.68, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 163840, + "canonical_id": "deepseek-2", + "size_b": 30.8, + "hf_id": "deepseek-ai/DeepSeek-V3.2-Exp", + "hf_private": false + }, + { + "name": "novita/moonshotai/kimi-k2-instruct", + "type": "chat", + "input_price_per_1m": 0.57, + "output_price_per_1m": 2.3, + "currency": "USD", + "context_window": 131072, + "canonical_id": "kimi-k2", + "size_b": 1026.5, + "hf_id": "moonshotai/Kimi-K2-Instruct-0905", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "novita/zai-org/glm-4.6", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.2, + "currency": "USD", + "context_window": 204800, + "canonical_id": "glm-4-6", + "size_b": 356.8, + "hf_id": "zai-org/GLM-4.6", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "novita/qwen/qwen3.5-397b-a17b", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3.6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "size_b": 397, + "canonical_id": "qwen3-5-397b-a17b", + "hf_id": "Qwen/Qwen3.5-397B-A17B", + "hf_private": false + }, + { + "name": "novita/minimax/minimax-m2.7-highspeed", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 204800, + "canonical_id": "minimax-m2-7-highspeed" + }, + { + "name": "novita/zai-org/glm-4.5", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.2, + "currency": "USD", + "context_window": 131072, + "canonical_id": "glm-4-5", + "size_b": 358.3, + "hf_id": "zai-org/GLM-4.5", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "parasail/Kimi K2.5", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.8, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-5", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.5", + "hf_private": false + }, + { + "name": "nebius/qwen/qwen3.5-397b-a17b", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3.6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "size_b": 397, + "canonical_id": "qwen3-5-397b-a17b", + "hf_id": "Qwen/Qwen3.5-397B-A17B", + "hf_private": false + }, + { + "name": "fireworks/kimi-k2.5", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-5", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.5", + "hf_private": false + }, + { + "name": "fireworks/nemotron-3-ultra-nvfp4", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 262144, + "canonical_id": "nemotron-3-ultra-nvfp4" + }, + { + "name": "deepinfra/zai-org/GLM-4.5", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.2, + "currency": "USD", + "context_window": 131072, + "canonical_id": "glm-4-5", + "size_b": 358.3, + "hf_id": "zai-org/GLM-4.5", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "moonshot/kimi-k2.5", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-5", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.5", + "hf_private": false + }, + { + "name": "vertex/kimi-k2", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2", + "size_b": 1026.5, + "hf_id": "moonshotai/Kimi-K2-Instruct-0905", + "hf_private": false + }, + { + "name": "bedrock/kimi-k2.5", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "canonical_id": "kimi-k2-5", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.5", + "hf_private": false + }, + { + "name": "minimaxi/MiniMax-M2.5-highspeed", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "minimax-m2-5-highspeed" + }, + { + "name": "minimaxi/MiniMax-M2.7-highspeed", + "type": "vision", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "minimax-m2-7-highspeed" + }, + { + "name": "zai/GLM-4.5", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 131072, + "canonical_id": "glm-4-5", + "size_b": 358.3, + "hf_id": "zai-org/GLM-4.5", + "hf_private": false + }, + { + "name": "zai/GLM-4.6", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "glm-4-6", + "size_b": 356.8, + "hf_id": "zai-org/GLM-4.6", + "hf_private": false + }, + { + "name": "zai/GLM-4.7", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 2.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "glm-4-7", + "size_b": 358.3, + "hf_id": "zai-org/GLM-4.7", + "hf_private": false + }, + { + "name": "novita/microsoft/wizardlm-2-8x22b", + "type": "chat", + "input_price_per_1m": 0.62, + "output_price_per_1m": 0.62, + "currency": "USD", + "context_window": 65535, + "size_b": 22, + "canonical_id": "wizardlm-2-8x22b", + "hf_id": "microsoft/WizardLM-2-8x22B", + "hf_private": false + }, + { + "name": "openai/gpt-5", + "type": "vision", + "input_price_per_1m": 0.625, + "output_price_per_1m": 5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5" + }, + { + "name": "novita/deepseek/deepseek-r1-turbo", + "type": "chat", + "input_price_per_1m": 0.7, + "output_price_per_1m": 2.5, + "currency": "USD", + "context_window": 64000, + "canonical_id": "deepseek-r1-turbo" + }, + { + "name": "novita/deepseek/deepseek-prover-v2-671b", + "type": "chat", + "input_price_per_1m": 0.7, + "output_price_per_1m": 2.5, + "currency": "USD", + "context_window": 160000, + "size_b": 671, + "canonical_id": "deepseek-prover-671b", + "hf_private": false + }, + { + "name": "parasail/parasail-qwen25-vl-72b-instruct", + "type": "vision", + "input_price_per_1m": 0.7, + "output_price_per_1m": 0.7, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 32768, + "size_b": 72, + "canonical_id": "parasail-qwen25-vl-72b", + "hf_private": false + }, + { + "name": "inceptron/kimi-k2.7-Code", + "type": "vision", + "input_price_per_1m": 0.75, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "kimi-k2-7-code", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.7-Code", + "hf_private": false + }, + { + "name": "parasail/kimi-k2.7-code", + "type": "vision", + "input_price_per_1m": 0.75, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-7-code", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.7-Code", + "hf_private": false + }, + { + "name": "openai/gpt-5.4-mini", + "type": "vision", + "input_price_per_1m": 0.75, + "output_price_per_1m": 4.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-4-mini" + }, + { + "name": "deepinfra/moonshotai/Kimi-K2.6", + "type": "vision", + "input_price_per_1m": 0.75, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-6", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.6", + "hf_private": false + }, + { + "name": "openai-responses/gpt-5.4-mini", + "type": "vision", + "input_price_per_1m": 0.75, + "output_price_per_1m": 4.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-4-mini" + }, + { + "name": "azure/gpt-5.4-mini", + "type": "chat", + "input_price_per_1m": 0.75, + "output_price_per_1m": 4.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-4-mini" + }, + { + "name": "inceptron/kimi-k2.6", + "type": "vision", + "input_price_per_1m": 0.8, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-6", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.6", + "hf_private": false + }, + { + "name": "novita/qwen/qwen2.5-vl-72b-instruct", + "type": "chat", + "input_price_per_1m": 0.8, + "output_price_per_1m": 0.8, + "currency": "USD", + "context_window": 96000, + "size_b": 72, + "canonical_id": "qwen2-5-vl-72b", + "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct", + "capabilities": [ + "vision" + ], + "hf_private": false + }, + { + "name": "novita/deepseek/deepseek-r1-distill-llama-70b", + "type": "chat", + "input_price_per_1m": 0.8, + "output_price_per_1m": 0.8, + "currency": "USD", + "context_window": 32000, + "size_b": 70, + "canonical_id": "deepseek-r1-distill-llama-70b", + "hf_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "capabilities": [ + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct", + "type": "chat", + "input_price_per_1m": 0.8, + "output_price_per_1m": 0.8, + "currency": "USD", + "context_window": 130815, + "size_b": 405, + "canonical_id": "meta-llama-3-1-405b", + "hf_id": "meta-llama/Llama-3.1-405B-Instruct", + "hf_private": false + }, + { + "name": "deepinfra/deepseek-ai/DeepSeek-R1", + "type": "chat", + "input_price_per_1m": 0.85, + "output_price_per_1m": 2.5, + "currency": "USD", + "context_window": 64000, + "canonical_id": "deepseek-r1", + "size_b": 671, + "size_source": "manual", + "hf_id": "deepseek-ai/DeepSeek-R1", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "deepinfra/deepseek-ai/DeepSeek-V3", + "type": "chat", + "input_price_per_1m": 0.85, + "output_price_per_1m": 0.9, + "currency": "USD", + "context_window": 128000, + "canonical_id": "deepseek", + "size_b": 685, + "hf_id": "deepseek-ai/DeepSeek-V3-0324", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "alibaba/qwen3-max", + "type": "vision", + "input_price_per_1m": 0.861, + "output_price_per_1m": 3.441, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 262144, + "canonical_id": "qwen3-max" + }, + { + "name": "novita/deepseek/deepseek_v3", + "type": "chat", + "input_price_per_1m": 0.89, + "output_price_per_1m": 0.89, + "currency": "USD", + "context_window": 64000, + "canonical_id": "deepseek", + "size_b": 685, + "hf_id": "deepseek-ai/DeepSeek-V3-0324", + "capabilities": [ + "tools" + ], + "hf_private": false + }, + { + "name": "nebius/moonshotai/kimi-k2.6", + "type": "vision", + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 256000, + "canonical_id": "kimi-k2-6", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.6", + "hf_private": false + }, + { + "name": "fireworks/kimi-k2.7-code", + "type": "vision", + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-7-code", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.7-Code", + "hf_private": false + }, + { + "name": "fireworks/kimi-k2.6", + "type": "vision", + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-6", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.6", + "hf_private": false + }, + { + "name": "moonshot/kimi-k2.7-code", + "type": "vision", + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-7-code", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.7-Code", + "hf_private": false + }, + { + "name": "moonshot/kimi-k2.6", + "type": "vision", + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-6", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.6", + "hf_private": false + }, + { + "name": "novita/GLM-5", + "type": "chat", + "input_price_per_1m": 1, + "output_price_per_1m": 3.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 202800, + "canonical_id": "glm-5", + "size_b": 753.9, + "hf_id": "zai-org/GLM-5", + "hf_private": false + }, + { + "name": "openai/o3", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o3" + }, + { + "name": "nebius/nvidia/nemotron-3-ultra-550b-a55b", + "type": "chat", + "input_price_per_1m": 1, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "size_b": 550, + "canonical_id": "nemotron-3-ultra-550b-a55b", + "hf_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "hf_private": false + }, + { + "name": "nebius/nousresearch/hermes-4-405b", + "type": "chat", + "input_price_per_1m": 1, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 128000, + "size_b": 405, + "canonical_id": "hermes-4-405b", + "hf_id": "NousResearch/Hermes-4-405B", + "hf_private": false + }, + { + "name": "xai/grok-build-0.1", + "type": "chat", + "input_price_per_1m": 1, + "output_price_per_1m": 2, + "currency": "USD", + "context_window": 256000, + "canonical_id": "grok-build-0-1", + "hf_private": true, + "capabilities": [ + "vision", + "tools", + "reasoning" + ] + }, + { + "name": "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro", + "type": "chat", + "input_price_per_1m": 1, + "output_price_per_1m": 3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "mimo-5-pro", + "size_b": 1023.2, + "size_source": "hf-total", + "hf_id": "XiaomiMiMo/MiMo-V2.5-Pro", + "hf_private": false + }, + { + "name": "anthropic/claude-haiku-4-5", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 200000, + "canonical_id": "claude-haiku-4-5", + "hf_private": true + }, + { + "name": "perplexity/sonar", + "type": "chat", + "input_price_per_1m": 1, + "output_price_per_1m": 1, + "currency": "USD", + "context_window": 131072, + "canonical_id": "sonar", + "hf_private": true, + "capabilities": [ + "vision" + ] + }, + { + "name": "vertex/claude-haiku-4-5", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 200000, + "canonical_id": "claude-haiku-4-5", + "hf_private": true + }, + { + "name": "vertex/gemini-3.1-pro-preview", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-1-pro", + "hf_private": true + }, + { + "name": "bedrock/claude-haiku-4-5", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 200000, + "canonical_id": "claude-haiku-4-5", + "hf_private": true + }, + { + "name": "alibaba/qwen3-coder-plus", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 5, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1048576, + "canonical_id": "qwen3-coder-plus" + }, + { + "name": "zai/GLM-5", + "type": "vision", + "input_price_per_1m": 1, + "output_price_per_1m": 3.2, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "glm-5", + "size_b": 753.9, + "hf_id": "zai-org/GLM-5", + "hf_private": false + }, + { + "name": "deepinfra/zai-org/GLM-5.1", + "type": "chat", + "input_price_per_1m": 1.05, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 202752, + "canonical_id": "glm-5-1", + "size_b": 753.9, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.1", + "hf_private": false + }, + { + "name": "doubleword/glm-5.2", + "type": "chat", + "input_price_per_1m": 1.05, + "output_price_per_1m": 3.3, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "hf_private": false + }, + { + "name": "openai/o3-mini", + "type": "chat", + "input_price_per_1m": 1.1, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o3-mini" + }, + { + "name": "openai-responses/o3-mini", + "type": "chat", + "input_price_per_1m": 1.1, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o3-mini" + }, + { + "name": "openai-responses/o4-mini", + "type": "chat", + "input_price_per_1m": 1.1, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o4-mini" + }, + { + "name": "azure/o4-mini", + "type": "chat", + "input_price_per_1m": 1.1, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o4-mini" + }, + { + "name": "inceptron/glm-5.2", + "type": "chat", + "input_price_per_1m": 1.2, + "output_price_per_1m": 4.2, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "hf_private": false + }, + { + "name": "deepinfra/Qwen/Qwen3-Max", + "type": "chat", + "input_price_per_1m": 1.2, + "output_price_per_1m": 6, + "currency": "USD", + "context_window": 256000, + "canonical_id": "qwen3-max", + "capabilities": [ + "tools" + ] + }, + { + "name": "google/gemini-2.5-pro", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-pro", + "hf_private": true + }, + { + "name": "openai/gpt-5.1", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-1" + }, + { + "name": "openai/gpt-5-chat", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "canonical_id": "gpt-5" + }, + { + "name": "openai/gpt-5.1-chat", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "canonical_id": "gpt-5-1" + }, + { + "name": "coding/gemini-2.5-pro", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-pro", + "hf_private": true + }, + { + "name": "xai/grok-4.3", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 2.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "grok-4-3", + "hf_private": true + }, + { + "name": "tensorx/kimi-k2.7-code", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 4.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "kimi-k2-7-code", + "size_b": 1058.6, + "size_source": "hf-total", + "hf_id": "moonshotai/Kimi-K2.7-Code", + "hf_private": false + }, + { + "name": "vertex/gemini-2.5-pro", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-2-5-pro", + "hf_private": true + }, + { + "name": "openai-responses/gpt-5", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5" + }, + { + "name": "openai-responses/gpt-5.1-codex", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-1-codex" + }, + { + "name": "openai-responses/gpt-5.1", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-1" + }, + { + "name": "openai-responses/gpt-5-codex", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-codex" + }, + { + "name": "azure/gpt-5", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "gpt-5" + }, + { + "name": "azure/gpt-5.1", + "type": "vision", + "input_price_per_1m": 1.25, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "gpt-5-1" + }, + { + "name": "deepinfra/deepseek-ai/DeepSeek-V4-Pro", + "type": "chat", + "input_price_per_1m": 1.3, + "output_price_per_1m": 2.6, + "currency": "USD", + "context_window": 1048576, + "canonical_id": "deepseek-pro", + "size_b": 861.6, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "doubleword/deepseek-v4-pro", + "type": "chat", + "input_price_per_1m": 1.31, + "output_price_per_1m": 2.75, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "deepseek-pro", + "size_b": 861.6, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "hf_private": false + }, + { + "name": "novita/zai-org/glm-5.1", + "type": "chat", + "input_price_per_1m": 1.38, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 204800, + "canonical_id": "glm-5-1", + "size_b": 753.9, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.1", + "hf_private": false + }, + { + "name": "nebius/zai-org/glm-5.1", + "type": "chat", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "glm-5-1", + "size_b": 753.9, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.1", + "hf_private": false + }, + { + "name": "nebius/glm-5.2", + "type": "chat", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "hf_private": false + }, + { + "name": "fireworks/glm-5.1", + "type": "chat", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "currency": "USD", + "context_window": 202000, + "canonical_id": "glm-5-1", + "size_b": 753.9, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.1", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "fireworks/glm-5.2", + "type": "chat", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "hf_private": false + }, + { + "name": "zai/glm-5.1", + "type": "vision", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "glm-5-1", + "size_b": 753.9, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.1", + "hf_private": false + }, + { + "name": "zai/glm-5.2", + "type": "vision", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "hf_private": false + }, + { + "name": "novita/sao10k/l31-70b-euryale-v2.2", + "type": "chat", + "input_price_per_1m": 1.48, + "output_price_per_1m": 1.48, + "currency": "USD", + "context_window": 16000, + "size_b": 70, + "canonical_id": "l31-70b-euryale-2", + "hf_private": false + }, + { + "name": "tensorx/glm-5.2", + "type": "chat", + "input_price_per_1m": 1.5, + "output_price_per_1m": 4.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "hf_private": false + }, + { + "name": "vertex/gemini-3.5-flash", + "type": "vision", + "input_price_per_1m": 1.5, + "output_price_per_1m": 9, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-5-flash", + "hf_private": true + }, + { + "name": "mistral/mistral-medium-3-5", + "type": "vision", + "input_price_per_1m": 1.5, + "output_price_per_1m": 7.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 262144, + "canonical_id": "mistral-medium-3-5" + }, + { + "name": "alibaba/qwen-max", + "type": "chat", + "input_price_per_1m": 1.6, + "output_price_per_1m": 6.4, + "currency": "USD", + "context_window": 32768, + "canonical_id": "qwen-max" + }, + { + "name": "fireworks/deepseek-v4-pro", + "type": "chat", + "input_price_per_1m": 1.74, + "output_price_per_1m": 3.48, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "deepseek-pro", + "size_b": 861.6, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "hf_private": false + }, + { + "name": "openai/gpt-5.2", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-2" + }, + { + "name": "openai/gpt-5.2-chat", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "canonical_id": "gpt-5-2" + }, + { + "name": "openai/gpt-5.3-chat", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "canonical_id": "gpt-5-3" + }, + { + "name": "nebius/deepseek-ai/deepseek-v4-pro", + "type": "chat", + "input_price_per_1m": 1.75, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 164000, + "canonical_id": "deepseek-pro", + "size_b": 861.6, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "hf_private": false + }, + { + "name": "tensorx/deepseek-v4-pro", + "type": "chat", + "input_price_per_1m": 1.75, + "output_price_per_1m": 3.5, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "deepseek-pro", + "size_b": 861.6, + "size_source": "hf-total", + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "hf_private": false + }, + { + "name": "openai-responses/gpt-5.3-codex", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-3-codex" + }, + { + "name": "openai-responses/gpt-5.3-chat", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 128000, + "canonical_id": "gpt-5-3" + }, + { + "name": "openai-responses/gpt-5.2-codex", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-2-codex" + }, + { + "name": "openai-responses/gpt-5.2", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-2" + }, + { + "name": "azure/gpt-5.2", + "type": "chat", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 200000, + "canonical_id": "gpt-5-2" + }, + { + "name": "azure/gpt-5.3-codex", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-3-codex" + }, + { + "name": "azure/gpt-5.2-codex", + "type": "vision", + "input_price_per_1m": 1.75, + "output_price_per_1m": 14, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-2-codex" + }, + { + "name": "novita/xiaomimimo/mimo-v2-pro", + "type": "chat", + "input_price_per_1m": 2, + "output_price_per_1m": 6, + "currency": "USD", + "capabilities": [ + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "mimo-pro" + }, + { + "name": "google/gemini-3.1-pro-preview", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 12, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-1-pro", + "hf_private": true + }, + { + "name": "google/gemini-3-pro-preview", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 12, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-pro", + "hf_private": true + }, + { + "name": "openai/gpt-4.1", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 8, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1" + }, + { + "name": "xai/grok-4.2-beta", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 6, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 2000000, + "canonical_id": "grok-4-2-beta", + "hf_private": true + }, + { + "name": "anthropic/claude-sonnet-5", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-5", + "hf_private": true + }, + { + "name": "perplexity/sonar-reasoning-pro", + "type": "chat", + "input_price_per_1m": 2, + "output_price_per_1m": 8, + "currency": "USD", + "context_window": 131072, + "canonical_id": "sonar-reasoning-pro", + "hf_private": true, + "capabilities": [ + "vision", + "reasoning" + ] + }, + { + "name": "vertex/claude-sonnet-5", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-5", + "hf_private": true + }, + { + "name": "vertex/gemini-3-pro-preview", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 12, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-pro", + "hf_private": true + }, + { + "name": "vertex/gemini-3-pro-image-preview", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 12, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1048576, + "canonical_id": "gemini-3-pro-image", + "hf_private": true + }, + { + "name": "bedrock/claude-sonnet-5", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-5", + "hf_private": true + }, + { + "name": "openai-responses/gpt-4.1", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 8, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1" + }, + { + "name": "mistral/pixtral-large-latest", + "type": "chat", + "input_price_per_1m": 2, + "output_price_per_1m": 5, + "currency": "USD", + "context_window": 131072, + "canonical_id": "pixtral-large" + }, + { + "name": "azure/openai-responses/gpt-4.1", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 8, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1" + }, + { + "name": "azure/gpt-4.1", + "type": "vision", + "input_price_per_1m": 2, + "output_price_per_1m": 8, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 1047576, + "canonical_id": "gpt-4-1" + }, + { + "name": "openai/gpt-4o-2024-05-13", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 128000, + "canonical_id": "gpt-4o-05-13" + }, + { + "name": "openai/gpt-4o", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 128000, + "canonical_id": "gpt-4o" + }, + { + "name": "openai/gpt-5.4", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4" + }, + { + "name": "openai/gpt-4o-2024-08-06", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 128000, + "canonical_id": "gpt-4o-08-06" + }, + { + "name": "openai/gpt-4o-2024-11-20", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 10, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 128000, + "canonical_id": "gpt-4o-11-20" + }, + { + "name": "alibaba/qwen3.7-max", + "type": "chat", + "input_price_per_1m": 2.5, + "output_price_per_1m": 7.5, + "currency": "USD", + "context_window": 1048576, + "canonical_id": "qwen3-7-max", + "capabilities": [ + "tools", + "reasoning" + ] + }, + { + "name": "openai-responses/gpt-5.4", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4" + }, + { + "name": "azure/openai-responses/gpt-5.4", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4" + }, + { + "name": "azure/gpt-5.4", + "type": "vision", + "input_price_per_1m": 2.5, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4" + }, + { + "name": "bedrock/gpt-5.4", + "type": "vision", + "input_price_per_1m": 2.75, + "output_price_per_1m": 16.5, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4" + }, + { + "name": "xai/grok-4", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision" + ], + "context_window": 256000, + "canonical_id": "grok-4", + "hf_private": true + }, + { + "name": "anthropic/claude-sonnet-4-6", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-4-6", + "hf_private": true + }, + { + "name": "anthropic/claude-sonnet-4-5", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-4-5", + "hf_private": true + }, + { + "name": "perplexity/sonar-pro", + "type": "chat", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "context_window": 204800, + "canonical_id": "sonar-pro", + "hf_private": true, + "capabilities": [ + "vision" + ] + }, + { + "name": "vertex/claude-sonnet-4-6", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-4-6", + "hf_private": true + }, + { + "name": "vertex/claude-sonnet-4-5", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-sonnet-4-5", + "hf_private": true + }, + { + "name": "vertex/claude-sonnet-4", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-sonnet-4", + "hf_private": true + }, + { + "name": "bedrock/claude-sonnet-4-5", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-sonnet-4-5", + "hf_private": true + }, + { + "name": "bedrock/claude-sonnet-4", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-sonnet-4", + "hf_private": true + }, + { + "name": "bedrock/claude-sonnet-4-6", + "type": "vision", + "input_price_per_1m": 3, + "output_price_per_1m": 15, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-sonnet-4-6", + "hf_private": true + }, + { + "name": "novita/deepseek/deepseek-r1", + "type": "chat", + "input_price_per_1m": 4, + "output_price_per_1m": 4, + "currency": "USD", + "context_window": 64000, + "canonical_id": "deepseek-r1", + "size_b": 671, + "size_source": "manual", + "hf_id": "deepseek-ai/DeepSeek-R1", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "openai/gpt-5.5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 30, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-5" + }, + { + "name": "xai/grok-3", + "type": "chat", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "context_window": 131072, + "canonical_id": "grok-3", + "hf_private": true + }, + { + "name": "anthropic/claude-opus-4-8", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-8", + "hf_private": true + }, + { + "name": "anthropic/claude-opus-4-5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-opus-4-5", + "hf_private": true + }, + { + "name": "anthropic/claude-opus-4-6", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-6", + "hf_private": true + }, + { + "name": "anthropic/claude-opus-4-7", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-7", + "hf_private": true + }, + { + "name": "sakana/fugu-ultra", + "type": "chat", + "input_price_per_1m": 5, + "output_price_per_1m": 30, + "currency": "USD", + "context_window": 1048576, + "canonical_id": "fugu-ultra", + "capabilities": [ + "vision", + "tools", + "reasoning" + ] + }, + { + "name": "vertex/claude-opus-4-8", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-8", + "hf_private": true + }, + { + "name": "vertex/claude-opus-4-7", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-7", + "hf_private": true + }, + { + "name": "vertex/claude-opus-4-5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-opus-4-5", + "hf_private": true + }, + { + "name": "vertex/claude-opus-4-6", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-6", + "hf_private": true + }, + { + "name": "bedrock/claude-opus-4-5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-opus-4-5", + "hf_private": true + }, + { + "name": "bedrock/claude-opus-4-7", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-7", + "hf_private": true + }, + { + "name": "bedrock/claude-opus-4-8", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-8", + "hf_private": true + }, + { + "name": "bedrock/claude-opus-4-6", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 25, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-opus-4-6", + "hf_private": true + }, + { + "name": "openai-responses/gpt-5.5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 30, + "currency": "USD", "capabilities": [ - "vision" + "vision", + "reasoning" ], - "hf_private": false, + "context_window": 1050000, + "canonical_id": "gpt-5-5" + }, + { + "name": "azure/openai-responses/gpt-5.5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 30, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-5" + }, + { + "name": "azure/gpt-5.5", + "type": "vision", + "input_price_per_1m": 5, + "output_price_per_1m": 30, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-5" + }, + { + "name": "bedrock/gpt-5.5", + "type": "vision", + "input_price_per_1m": 5.5, + "output_price_per_1m": 33, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-5" + }, + { + "name": "anthropic/claude-fable-5", + "type": "vision", + "input_price_per_1m": 10, + "output_price_per_1m": 50, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-fable-5", + "hf_private": true + }, + { + "name": "vertex/claude-fable-5", + "type": "vision", + "input_price_per_1m": 10, + "output_price_per_1m": 50, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-fable-5", + "hf_private": true + }, + { + "name": "bedrock/claude-fable-5", + "type": "vision", + "input_price_per_1m": 11, + "output_price_per_1m": 55, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1000000, + "canonical_id": "claude-fable-5", + "hf_private": true + }, + { + "name": "openai/o1", + "type": "vision", + "input_price_per_1m": 15, + "output_price_per_1m": 60, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o1" + }, + { + "name": "anthropic/claude-opus-4-1", + "type": "vision", + "input_price_per_1m": 15, + "output_price_per_1m": 75, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-opus-4-1", + "hf_private": true + }, + { + "name": "vertex/claude-opus-4-1", + "type": "vision", + "input_price_per_1m": 15, + "output_price_per_1m": 75, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-opus-4-1", + "hf_private": true + }, + { + "name": "vertex/claude-opus-4", + "type": "vision", + "input_price_per_1m": 15, + "output_price_per_1m": 75, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "claude-opus-4", + "hf_private": true + }, + { + "name": "openai-responses/gpt-5-pro", + "type": "vision", + "input_price_per_1m": 15, + "output_price_per_1m": 120, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 400000, + "canonical_id": "gpt-5-pro" + }, + { + "name": "openai-responses/o3-pro", + "type": "vision", + "input_price_per_1m": 20, + "output_price_per_1m": 80, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 200000, + "canonical_id": "o3-pro" + }, + { + "name": "openai-responses/gpt-5.5-pro", + "type": "vision", + "input_price_per_1m": 30, + "output_price_per_1m": 180, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-5-pro" + }, + { + "name": "openai-responses/gpt-5.4-pro", + "type": "vision", + "input_price_per_1m": 30, + "output_price_per_1m": 180, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4-pro" + }, + { + "name": "azure/openai-responses/gpt-5.4-pro", + "type": "vision", + "input_price_per_1m": 30, + "output_price_per_1m": 180, + "currency": "USD", + "capabilities": [ + "vision", + "reasoning" + ], + "context_window": 1050000, + "canonical_id": "gpt-5-4-pro" + } + ], + "lastUpdated": "2026-03-02T04:53:24.807Z" + }, + { + "name": "Nebius", + "url": "https://nebius.ai/services/token-factory/pricing", + "headquarters": "Netherlands", + "region": "EU", + "gdpr_compliant": true, + "eu_endpoints": true, + "models": [ + { + "name": "Qwen/Qwen3-Embedding-8B", + "type": "embedding", + "currency": "USD", + "input_price_per_1m": 0.01, + "output_price_per_1m": 0, + "context_window": 40960, + "hf_id": "Qwen/Qwen3-Embedding-8B", + "size_b": 8, + "canonical_id": "qwen3-embedding-8b" + }, + { + "name": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.06, + "output_price_per_1m": 0.24, + "context_window": 262144, + "hf_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", + "size_b": 30, + "canonical_id": "nvidia-nemotron-3-nano-30b-a3b" + }, + { + "name": "nvidia/Nemotron-3-Nano-Omni", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.06, + "output_price_per_1m": 0.24, + "context_window": 8000, + "hf_id": "nvidia/Nemotron-3-Nano-Omni", + "canonical_id": "nemotron-3-nano-omni" + }, + { + "name": "Qwen/Qwen3-32B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, + "context_window": 40960, + "hf_id": "Qwen/Qwen3-32B", + "size_b": 32, + "canonical_id": "qwen3-32b" + }, + { + "name": "google/gemma-3-27b-it", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, + "context_window": 110000, "hf_id": "google/gemma-3-27b-it", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, + "size_b": 27, "canonical_id": "gemma-3-27b" }, { - "name": "gemma-3-27b-it-fast", - "type": "vision", + "name": "Qwen/Qwen3-30B-A3B-Instruct-2507", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, + "context_window": 262144, + "hf_id": "Qwen/Qwen3-30B-A3B-Instruct-2507", + "size_b": 30, + "canonical_id": "qwen3-30b-a3b" + }, + { + "name": "nvidia/Cosmos3-Super-Reasoner", + "type": "vision", + "currency": "USD", + "capabilities": [ + "vision" + ], + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.3, + "context_window": 8000, + "hf_id": "nvidia/Cosmos3-Super-Reasoner", + "canonical_id": "cosmos3-super-reasoner" + }, + { + "name": "meta-llama/Llama-3.3-70B-Instruct", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.4, + "context_window": 131072, + "hf_id": "meta-llama/Llama-3.3-70B-Instruct", + "size_b": 70, + "canonical_id": "llama-3-3-70b" + }, + { + "name": "NousResearch/Hermes-4-70B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.4, + "context_window": 131072, + "hf_id": "NousResearch/Hermes-4-70B", + "size_b": 70, + "canonical_id": "hermes-4-70b" + }, + { + "name": "openai/gpt-oss-120b", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "context_window": 131072, + "hf_id": "openai/gpt-oss-120b", + "size_b": 120, + "canonical_id": "gpt-oss-120b" + }, + { + "name": "Qwen/Qwen3-Next-80B-A3B-Thinking", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.15, + "output_price_per_1m": 1.2, + "context_window": 8000, + "hf_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", + "size_b": 80, + "canonical_id": "qwen3-next-80b-a3b" + }, + { + "name": "Qwen/Qwen3-235B-A22B-Instruct-2507", + "type": "chat", + "currency": "USD", "input_price_per_1m": 0.2, "output_price_per_1m": 0.6, + "context_window": 262144, + "hf_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", + "size_b": 235, + "canonical_id": "qwen3-235b-a22b" + }, + { + "name": "Qwen/Qwen2.5-VL-72B-Instruct", + "type": "vision", "currency": "USD", - "size_b": 27, "capabilities": [ "vision" ], - "hf_private": false, - "canonical_id": "gemma-3-27b-fast" + "input_price_per_1m": 0.25, + "output_price_per_1m": 0.75, + "context_window": 32000, + "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct", + "size_b": 72, + "canonical_id": "qwen2-5-vl-72b" + }, + { + "name": "nvidia/nemotron-3-super-120b-a12b", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.9, + "context_window": 262144, + "hf_id": "nvidia/nemotron-3-super-120b-a12b", + "size_b": 120, + "canonical_id": "nemotron-3-super-120b-a12b" + }, + { + "name": "MiniMaxAI/MiniMax-M2.5", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.3, + "output_price_per_1m": 1.2, + "context_window": 8000, + "hf_id": "MiniMaxAI/MiniMax-M2.5", + "canonical_id": "minimax-m2-5" + }, + { + "name": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.6, + "output_price_per_1m": 1.8, + "context_window": 8000, + "hf_id": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", + "size_b": 253, + "canonical_id": "llama-3-1-nemotron-ultra-253b" + }, + { + "name": "Qwen/Qwen3.5-397B-A17B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3.6, + "context_window": 8000, + "hf_id": "Qwen/Qwen3.5-397B-A17B", + "size_b": 397, + "canonical_id": "qwen3-5-397b-a17b" }, { - "name": "llava-1.5-7b-hf", + "name": "openbmb/MiniCPM-V-4_5", "type": "vision", - "input_price_per_1m": 0.04, - "output_price_per_1m": 0.12, "currency": "USD", - "size_b": 7, "capabilities": [ "vision" ], - "hf_private": false, - "canonical_id": "llava-1-5-7b-hf" + "input_price_per_1m": 0.658, + "output_price_per_1m": 1.11, + "context_window": 8000, + "hf_id": "openbmb/MiniCPM-V-4_5", + "canonical_id": "minicpm-v-4-5" }, { - "name": "llava-1.5-13b-hf", + "name": "moonshotai/Kimi-K2.6", "type": "vision", - "input_price_per_1m": 0.04, - "output_price_per_1m": 0.12, "currency": "USD", - "size_b": 13, "capabilities": [ "vision" ], + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "context_window": 8000, + "hf_id": "moonshotai/Kimi-K2.6", + "canonical_id": "kimi-k2-6" + }, + { + "name": "moonshotai/Kimi-K2.7-Code", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.95, + "output_price_per_1m": 4, + "context_window": 262144, + "hf_id": "moonshotai/Kimi-K2.7-Code", + "canonical_id": "kimi-k2-7-code" + }, + { + "name": "NousResearch/Hermes-4-405B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 1, + "output_price_per_1m": 3, + "context_window": 131072, + "hf_id": "NousResearch/Hermes-4-405B", + "size_b": 405, + "canonical_id": "hermes-4-405b" + }, + { + "name": "nvidia/Nemotron-3-Ultra-550b-a55b", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 1, + "output_price_per_1m": 3, + "context_window": 8000, + "hf_id": "nvidia/Nemotron-3-Ultra-550b-a55b", + "size_b": 550, + "canonical_id": "nemotron-3-ultra-550b-a55b" + }, + { + "name": "zai-org/GLM-5.1", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "context_window": 202752, + "hf_id": "zai-org/GLM-5.1", + "canonical_id": "glm-5-1" + }, + { + "name": "zai-org/GLM-5.2", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 1.4, + "output_price_per_1m": 4.4, + "context_window": 1048576, + "hf_id": "zai-org/GLM-5.2", + "canonical_id": "glm-5-2" + }, + { + "name": "deepseek-ai/DeepSeek-V4-Pro", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 1.75, + "output_price_per_1m": 3.5, + "context_window": 1048576, + "hf_id": "deepseek-ai/DeepSeek-V4-Pro", + "canonical_id": "deepseek-pro" + } + ], + "lastUpdated": "2026-07-03T07:24:12.271Z" + }, + { + "name": "Scaleway", + "url": "https://www.scaleway.com/en/generative-api/", + "headquarters": "France", + "region": "EU", + "gdpr_compliant": true, + "eu_endpoints": true, + "models": [ + { + "name": "glm-5.2", + "type": "chat", + "currency": "EUR", + "input_price_per_1m": 1.8, + "output_price_per_1m": 5.5, + "canonical_id": "glm-5-2", + "size_b": 753.3, + "size_source": "hf-total", + "hf_id": "zai-org/GLM-5.2", + "capabilities": [ + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "qwen3.5-397b-a17b", + "type": "chat", + "input_price_per_1m": 0.6, + "output_price_per_1m": 3.6, + "currency": "EUR", + "size_b": 397, + "capabilities": [ + "vision", + "video", + "tools", + "reasoning" + ], + "hf_id": "Qwen/Qwen3.5-397B-A17B", + "hf_private": false, + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "qwen3-5-397b-a17b" + }, + { + "name": "qwen3.6-35b-a3b", + "type": "chat", + "currency": "EUR", + "input_price_per_1m": 0.25, + "output_price_per_1m": 1.5, + "size_b": 35, + "canonical_id": "qwen3-6-35b-a3b", + "hf_id": "Qwen/Qwen3.6-35B-A3B", + "capabilities": [ + "vision", + "video", + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "gemma-4-26b-a4b-it", + "type": "chat", + "currency": "EUR", + "input_price_per_1m": 0.25, + "output_price_per_1m": 0.5, + "size_b": 26, + "canonical_id": "gemma-4-26b-a4b", + "hf_id": "google/gemma-4-26B-A4B-it", + "capabilities": [ + "vision", + "video", + "tools", + "reasoning" + ], + "hf_private": false + }, + { + "name": "mistral-medium-3.5-128b", + "type": "chat", + "currency": "EUR", + "input_price_per_1m": 1.5, + "output_price_per_1m": 7.5, + "size_b": 128, + "canonical_id": "mistral-medium-3-5-128b", + "hf_private": false + }, + { + "name": "whisper-large-v3", + "type": "audio", + "currency": "EUR", + "hf_id": "openai/whisper-large-v3", + "size_b": 1.55, + "hf_private": false, + "price_per_minute": 0.003, + "size_source": "manual", + "capabilities": [ + "audio" + ], + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "whisper-large" + }, + { + "name": "llama-3.3-70b-instruct", + "type": "chat", + "input_price_per_1m": 0.9, + "output_price_per_1m": 0.9, + "currency": "EUR", + "size_b": 70, + "capabilities": [ + "tools" + ], + "hf_private": false, + "hf_id": "meta-llama/Llama-3.3-70B-Instruct", + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "llama-3-3-70b" + }, + { + "name": "qwen3-235b-a22b-instruct-2507", + "type": "chat", + "input_price_per_1m": 0.75, + "output_price_per_1m": 2.25, + "currency": "EUR", + "size_b": 235, + "capabilities": [ + "tools", + "reasoning" + ], + "hf_id": "Qwen/Qwen3-235B-A22B", "hf_private": false, - "canonical_id": "llava-1-5-13b-hf" + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "qwen3-235b-a22b" }, { - "name": "Qwen2-VL-72B-Instruct", - "type": "vision", - "input_price_per_1m": 0.13, - "output_price_per_1m": 0.4, - "currency": "USD", - "size_b": 72, + "name": "qwen3-coder-30b-a3b-instruct", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.8, + "currency": "EUR", + "size_b": 30, "capabilities": [ - "vision" + "tools" ], - "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct", + "hf_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "hf_private": false, "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "qwen2-vl-72b" + "canonical_id": "qwen3-coder-30b-a3b" }, { - "name": "Qwen2-VL-7B-Instruct", - "type": "vision", - "input_price_per_1m": 0.04, - "output_price_per_1m": 0.12, - "currency": "USD", - "size_b": 7, + "name": "qwen3-embedding-8b", + "type": "embedding", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0, + "currency": "EUR", + "size_b": 8, + "hf_private": false, + "hf_id": "Qwen/Qwen3-Embedding-8B", + "hf_validated_at": "2026-03-22T19:58:46.149Z", + "hf_status": 200, + "canonical_id": "qwen3-embedding-8b" + }, + { + "name": "pixtral-12b-2409", + "type": "chat", + "input_price_per_1m": 0.2, + "output_price_per_1m": 0.2, + "currency": "EUR", + "size_b": 12, "capabilities": [ "vision" ], + "hf_id": "mistralai/Pixtral-12B-2409", "hf_private": false, - "canonical_id": "qwen2-vl-7b" + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "pixtral-12b" }, { - "name": "flux-schnell", - "type": "image", - "input_price_per_1m": 0.0013, - "output_price_per_1m": 0, - "currency": "USD", + "name": "voxtral-small-24b-2507", + "type": "audio", + "currency": "EUR", + "size_b": 24, "capabilities": [ - "image-gen" + "audio", + "tools" ], - "size_b": 12, - "size_source": "manual", + "hf_id": "mistralai/Voxtral-Small-24B-2507", "hf_private": false, - "hf_id": "black-forest-labs/FLUX.1-schnell", - "hf_validated_at": "2026-03-22T19:50:44.558Z", + "price_per_minute": 0.15, + "size_source": "manual", + "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "flux-schnell" + "canonical_id": "voxtral-small-24b" }, { - "name": "flux-dev", - "type": "image", - "input_price_per_1m": 0.007, - "output_price_per_1m": 0, - "currency": "USD", + "name": "mistral-small-3.2-24b-instruct-2506", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.35, + "currency": "EUR", + "size_b": 24, "capabilities": [ - "image-gen" + "vision", + "tools" ], - "size_b": 12, - "size_source": "manual", + "hf_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "hf_private": false, - "hf_id": "black-forest-labs/FLUX.1-dev", - "hf_validated_at": "2026-03-22T19:58:46.149Z", + "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "flux-dev" + "canonical_id": "mistral-small-3-2-24b" }, { - "name": "sdxl", - "type": "image", - "input_price_per_1m": 0.003, - "output_price_per_1m": 0, - "currency": "USD", + "name": "devstral-2-123b-instruct-2512", + "type": "chat", + "input_price_per_1m": 0.4, + "output_price_per_1m": 2, + "currency": "EUR", + "size_b": 123, + "hf_private": false, + "size_source": "manual", + "hf_id": "mistralai/Devstral-2-123B-Instruct-2512", "capabilities": [ - "image-gen" + "tools" ], - "hf_id": "stabilityai/stable-diffusion-xl-base-1.0", - "size_b": 2.6, - "size_source": "manual", - "hf_private": false, "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "sdxl" + "canonical_id": "devstral-2-123b" }, { - "name": "bge-multilingual-gemma2", - "type": "embedding", - "input_price_per_1m": 0.01, - "output_price_per_1m": 0, - "currency": "USD", - "hf_id": "BAAI/bge-multilingual-gemma2", - "size_b": 7.4, + "name": "gpt-oss-120b", + "type": "chat", + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.6, + "currency": "EUR", + "size_b": 120, + "capabilities": [ + "tools", + "reasoning" + ], + "hf_id": "openai/gpt-oss-120b", "hf_private": false, "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "bge-multilingual-gemma2" + "canonical_id": "gpt-oss-120b" }, { - "name": "bge-en-icl", - "type": "embedding", - "input_price_per_1m": 0.01, - "output_price_per_1m": 0, - "currency": "USD", - "size_b": 7.1, - "hf_id": "BAAI/bge-en-icl", + "name": "gemma-3-27b-it", + "type": "chat", + "input_price_per_1m": 0.25, + "output_price_per_1m": 0.5, + "currency": "EUR", + "size_b": 27, + "capabilities": [ + "vision" + ], "hf_private": false, + "hf_id": "google/gemma-3-27b-it", "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "bge-en-icl" + "canonical_id": "gemma-3-27b" }, { - "name": "e5-mistral-7b-instruct", + "name": "bge-multilingual-gemma2", "type": "embedding", - "input_price_per_1m": 0.01, + "input_price_per_1m": 0.1, "output_price_per_1m": 0, - "currency": "USD", - "size_b": 7, + "currency": "EUR", + "hf_id": "BAAI/bge-multilingual-gemma2", + "size_b": 7.4, "hf_private": false, - "hf_id": "intfloat/e5-mistral-7b-instruct", "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, - "canonical_id": "e5-mistral-7b" + "canonical_id": "bge-multilingual-gemma2", + "size_source": "hf-total" }, { - "name": "Llama-Guard-3-8B", + "name": "holo2-30b-a3b", "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 0.6, - "currency": "USD", - "size_b": 8, + "input_price_per_1m": 0.3, + "output_price_per_1m": 0.7, + "currency": "EUR", + "size_b": 30, "hf_private": false, - "hf_id": "meta-llama/Llama-Guard-3-8B", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "llama-guard-3-8b" + "canonical_id": "holo2-30b-a3b" } - ], - "lastUpdated": "2026-03-02T05:29:01.094Z" + ] }, { - "name": "Scaleway", - "url": "https://www.scaleway.com/en/generative-api/", + "name": "OVHcloud", + "url": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/", "headquarters": "France", "region": "EU", "gdpr_compliant": true, "eu_endpoints": true, "models": [ { - "name": "glm-5.2", + "name": "bge-multilingual-gemma2", + "type": "embedding", + "currency": "EUR", + "input_price_per_1m": 0.01, + "output_price_per_1m": 0, + "hf_id": "BAAI/bge-multilingual-gemma2", + "canonical_id": "bge-multilingual-gemma2", + "size_b": 9.2, + "size_source": "hf-total", + "hf_private": false + }, + { + "name": "nvr-tts-en-us", + "type": "audio", + "currency": "EUR", + "capabilities": [ + "audio" + ], + "input_price_per_1m": 0, + "output_price_per_1m": 0, + "canonical_id": "nvr-tts-en-us" + }, + { + "name": "Mistral-Small-3.2-24B-Instruct-2506", + "type": "vision", + "currency": "EUR", + "capabilities": [ + "vision", + "tools" + ], + "input_price_per_1m": 0.09, + "output_price_per_1m": 0.28, + "hf_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", + "size_b": 24, + "canonical_id": "mistral-small-3-2-24b", + "hf_private": false + }, + { + "name": "Qwen3Guard-Gen-8B", + "type": "chat", + "currency": "EUR", + "input_price_per_1m": 0, + "output_price_per_1m": 0, + "hf_id": "Qwen/Qwen3Guard-Gen-8B", + "size_b": 8, + "canonical_id": "qwen3guard-gen-8b", + "hf_private": false + }, + { + "name": "Meta-Llama-3_3-70B-Instruct", + "type": "chat", + "currency": "EUR", + "capabilities": [ + "tools" + ], + "input_price_per_1m": 0.67, + "output_price_per_1m": 0.67, + "hf_id": "meta-llama/Llama-3.3-70B-Instruct", + "size_b": 70, + "canonical_id": "meta-llama-3-3-70b", + "hf_private": false + }, + { + "name": "nvr-tts-es-es", + "type": "audio", + "currency": "EUR", + "capabilities": [ + "audio" + ], + "input_price_per_1m": 0, + "output_price_per_1m": 0, + "canonical_id": "nvr-tts-es-es" + }, + { + "name": "Qwen3-Embedding-8B", + "type": "embedding", + "currency": "EUR", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0, + "hf_id": "Qwen/Qwen3-Embedding-8B", + "size_b": 8, + "canonical_id": "qwen3-embedding-8b", + "hf_private": false + }, + { + "name": "stable-diffusion-xl-base-v10", + "type": "image", + "currency": "EUR", + "capabilities": [ + "image-gen" + ], + "price_per_image": 0, + "hf_id": "stabilityai/stable-diffusion-xl-base-1.0", + "canonical_id": "stable-diffusion-xl-base", + "hf_private": false + }, + { + "name": "bge-m3", + "type": "embedding", + "currency": "EUR", + "input_price_per_1m": 0.01, + "output_price_per_1m": 0, + "hf_id": "BAAI/bge-m3", + "canonical_id": "bge-m3", + "size_b": 0.57, + "size_source": "manual", + "hf_private": false + }, + { + "name": "gpt-oss-120b", "type": "chat", "currency": "EUR", - "input_price_per_1m": 1.8, - "output_price_per_1m": 5.5, - "canonical_id": "glm-5-2", - "size_b": 753.3, - "size_source": "hf-total", - "hf_id": "zai-org/GLM-5.2", "capabilities": [ "tools", "reasoning" ], + "input_price_per_1m": 0.08, + "output_price_per_1m": 0.4, + "hf_id": "openai/gpt-oss-120b", + "size_b": 120, + "canonical_id": "gpt-oss-120b", "hf_private": false }, { - "name": "qwen3.5-397b-a17b", + "name": "gpt-oss-20b", "type": "chat", - "input_price_per_1m": 0.6, - "output_price_per_1m": 3.6, "currency": "EUR", - "size_b": 397, "capabilities": [ - "vision", - "video", "tools", "reasoning" ], - "hf_id": "Qwen/Qwen3.5-397B-A17B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-5-397b-a17b" + "input_price_per_1m": 0.04, + "output_price_per_1m": 0.15, + "hf_id": "openai/gpt-oss-20b", + "size_b": 20, + "canonical_id": "gpt-oss-20b", + "hf_private": false }, { - "name": "qwen3.6-35b-a3b", - "type": "chat", + "name": "Qwen3.6-27B", + "type": "vision", "currency": "EUR", - "input_price_per_1m": 0.25, - "output_price_per_1m": 1.5, - "size_b": 35, - "canonical_id": "qwen3-6-35b-a3b", - "hf_id": "Qwen/Qwen3.6-35B-A3B", "capabilities": [ "vision", - "video", "tools", "reasoning" ], + "input_price_per_1m": 0.4, + "output_price_per_1m": 2.7, + "hf_id": "Qwen/Qwen3.6-27B", + "size_b": 27, + "canonical_id": "qwen3-6-27b", "hf_private": false }, { - "name": "gemma-4-26b-a4b-it", - "type": "chat", + "name": "whisper-large-v3", + "type": "audio", "currency": "EUR", - "input_price_per_1m": 0.25, - "output_price_per_1m": 0.5, - "size_b": 26, - "canonical_id": "gemma-4-26b-a4b", - "hf_id": "google/gemma-4-26B-A4B-it", "capabilities": [ - "vision", - "video", - "tools", - "reasoning" + "audio" ], + "price_per_minute": 0.00245, + "hf_id": "openai/whisper-large-v3", + "canonical_id": "whisper-large", + "size_b": 1.55, + "size_source": "manual", "hf_private": false }, { - "name": "mistral-medium-3.5-128b", - "type": "chat", + "name": "Qwen3.5-9B", + "type": "vision", "currency": "EUR", - "input_price_per_1m": 1.5, - "output_price_per_1m": 7.5, - "size_b": 128, - "canonical_id": "mistral-medium-3-5-128b", + "capabilities": [ + "vision", + "tools", + "reasoning" + ], + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.15, + "hf_id": "Qwen/Qwen3.5-9B", + "size_b": 9, + "canonical_id": "qwen3-5-9b", "hf_private": false }, { - "name": "whisper-large-v3", + "name": "whisper-large-v3-turbo", "type": "audio", "currency": "EUR", - "hf_id": "openai/whisper-large-v3", - "size_b": 1.55, - "hf_private": false, - "price_per_minute": 0.003, - "size_source": "manual", "capabilities": [ "audio" ], - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "whisper-large" + "price_per_minute": 0.000767, + "hf_id": "openai/whisper-large-v3-turbo", + "canonical_id": "whisper-large-turbo", + "size_b": 0.81, + "size_source": "manual", + "hf_private": false }, { - "name": "llama-3.3-70b-instruct", - "type": "chat", - "input_price_per_1m": 0.9, - "output_price_per_1m": 0.9, + "name": "Qwen3.5-397B-A17B", + "type": "vision", "currency": "EUR", - "size_b": 70, "capabilities": [ - "tools" + "vision", + "tools", + "reasoning" ], - "hf_private": false, - "hf_id": "meta-llama/Llama-3.3-70B-Instruct", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "llama-3-3-70b" + "input_price_per_1m": 0.6, + "output_price_per_1m": 3.6, + "hf_id": "Qwen/Qwen3.5-397B-A17B", + "size_b": 397, + "canonical_id": "qwen3-5-397b-a17b", + "hf_private": false }, { - "name": "qwen3-235b-a22b-instruct-2507", - "type": "chat", - "input_price_per_1m": 0.75, - "output_price_per_1m": 2.25, + "name": "nvr-tts-it-it", + "type": "audio", "currency": "EUR", - "size_b": 235, "capabilities": [ - "tools", - "reasoning" + "audio" ], - "hf_id": "Qwen/Qwen3-235B-A22B", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-235b-a22b" + "input_price_per_1m": 0, + "output_price_per_1m": 0, + "canonical_id": "nvr-tts" }, { - "name": "qwen3-coder-30b-a3b-instruct", - "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 0.8, + "name": "Qwen2.5-VL-72B-Instruct", + "type": "vision", "currency": "EUR", - "size_b": 30, "capabilities": [ - "tools" + "vision" ], - "hf_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "qwen3-coder-30b-a3b" + "input_price_per_1m": 0.91, + "output_price_per_1m": 0.91, + "hf_id": "Qwen/Qwen2.5-VL-72B-Instruct", + "size_b": 72, + "canonical_id": "qwen2-5-vl-72b", + "hf_private": false }, { - "name": "qwen3-embedding-8b", - "type": "embedding", - "input_price_per_1m": 0.1, + "name": "Qwen3Guard-Gen-0.6B", + "type": "chat", + "currency": "EUR", + "input_price_per_1m": 0, "output_price_per_1m": 0, + "hf_id": "Qwen/Qwen3Guard-Gen-0.6B", + "size_b": 0.6, + "canonical_id": "qwen3guard-gen-0-6b", + "hf_private": false + }, + { + "name": "nvr-tts-de-de", + "type": "audio", "currency": "EUR", - "size_b": 8, - "hf_private": false, - "hf_id": "Qwen/Qwen3-Embedding-8B", - "hf_validated_at": "2026-03-22T19:58:46.149Z", - "hf_status": 200, - "canonical_id": "qwen3-embedding-8b" + "capabilities": [ + "audio" + ], + "input_price_per_1m": 0, + "output_price_per_1m": 0, + "canonical_id": "nvr-tts-de-de" }, { - "name": "pixtral-12b-2409", + "name": "Mistral-Nemo-Instruct-2407", "type": "chat", - "input_price_per_1m": 0.2, - "output_price_per_1m": 0.2, "currency": "EUR", - "size_b": 12, "capabilities": [ - "vision" + "tools" ], - "hf_id": "mistralai/Pixtral-12B-2409", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "pixtral-12b" - }, + "input_price_per_1m": 0.13, + "output_price_per_1m": 0.13, + "hf_id": "mistralai/Mistral-Nemo-Instruct-2407", + "canonical_id": "mistral-nemo", + "size_b": 12.2, + "size_source": "hf-total", + "hf_private": false + } + ], + "lastUpdated": "2026-07-03T03:05:07.295Z" + }, + { + "name": "STACKIT", + "url": "https://stackit.com/en/products/data-ai/stackit-ai-model-serving", + "headquarters": "Germany", + "region": "EU", + "gdpr_compliant": true, + "eu_endpoints": true, + "models": [ { - "name": "voxtral-small-24b-2507", - "type": "audio", + "name": "Qwen3-VL 235B", + "type": "vision", "currency": "EUR", - "size_b": 24, + "input_price_per_1m": 1.5, + "output_price_per_1m": 1.75, "capabilities": [ - "audio", + "vision", "tools" ], - "hf_id": "mistralai/Voxtral-Small-24B-2507", - "hf_private": false, - "price_per_minute": 0.15, - "size_source": "manual", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "voxtral-small-24b" + "hf_id": "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", + "size_b": 235, + "canonical_id": "qwen3-vl-235b", + "hf_private": false }, { - "name": "mistral-small-3.2-24b-instruct-2506", + "name": "Qwen3.6 27B", "type": "chat", - "input_price_per_1m": 0.15, - "output_price_per_1m": 0.35, "currency": "EUR", - "size_b": 24, + "input_price_per_1m": 0.45, + "output_price_per_1m": 0.65, "capabilities": [ - "vision", "tools" ], - "hf_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "mistral-small-3-2-24b" + "hf_id": "Qwen/Qwen3.6-27B", + "size_b": 27, + "canonical_id": "qwen3-6-27b", + "hf_private": false }, { - "name": "devstral-2-123b-instruct-2512", + "name": "Llama 3.3 70B", "type": "chat", - "input_price_per_1m": 0.4, - "output_price_per_1m": 2, "currency": "EUR", - "size_b": 123, - "hf_private": false, - "size_source": "manual", - "hf_id": "mistralai/Devstral-2-123B-Instruct-2512", + "input_price_per_1m": 0.45, + "output_price_per_1m": 0.65, "capabilities": [ "tools" ], - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "devstral-2-123b" + "hf_id": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", + "size_b": 70.6, + "canonical_id": "llama-3-3-70b", + "hf_private": false }, { - "name": "gpt-oss-120b", + "name": "GPT-OSS 120B", "type": "chat", - "input_price_per_1m": 0.15, - "output_price_per_1m": 0.6, "currency": "EUR", - "size_b": 120, + "input_price_per_1m": 0.45, + "output_price_per_1m": 0.65, "capabilities": [ "tools", "reasoning" ], "hf_id": "openai/gpt-oss-120b", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "gpt-oss-120b" + "size_b": 120, + "canonical_id": "gpt-oss-120b", + "hf_private": false + }, + { + "name": "Gemma 3 27B", + "type": "vision", + "currency": "EUR", + "input_price_per_1m": 0.45, + "output_price_per_1m": 0.65, + "capabilities": [ + "vision" + ], + "hf_id": "google/gemma-3-27b-it", + "size_b": 27.4, + "canonical_id": "gemma-3-27b", + "hf_private": false }, { - "name": "gemma-3-27b-it", + "name": "GPT-OSS 20B", "type": "chat", - "input_price_per_1m": 0.25, - "output_price_per_1m": 0.5, "currency": "EUR", - "size_b": 27, + "input_price_per_1m": 0.15, + "output_price_per_1m": 0.25, "capabilities": [ - "vision" + "tools", + "reasoning" ], - "hf_private": false, - "hf_id": "google/gemma-3-27b-it", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "gemma-3-27b" + "hf_id": "openai/gpt-oss-20b", + "size_b": 20, + "canonical_id": "gpt-oss-20b", + "hf_private": false }, { - "name": "bge-multilingual-gemma2", + "name": "E5 Mistral 7B", "type": "embedding", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0, "currency": "EUR", - "hf_id": "BAAI/bge-multilingual-gemma2", - "size_b": 7.4, - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "bge-multilingual-gemma2" + "input_price_per_1m": 0.02, + "output_price_per_1m": 0, + "hf_id": "intfloat/e5-mistral-7b-instruct", + "size_b": 7, + "canonical_id": "e5-mistral-7b", + "hf_private": false }, { - "name": "holo2-30b-a3b", - "type": "chat", - "input_price_per_1m": 0.3, - "output_price_per_1m": 0.7, + "name": "Qwen3 Vision-Language Embedding", + "type": "embedding", "currency": "EUR", - "size_b": 30, - "hf_private": false, - "canonical_id": "holo2-30b-a3b" + "input_price_per_1m": 0.08, + "output_price_per_1m": 0, + "capabilities": [ + "vision" + ], + "hf_id": "Qwen/Qwen3-VL-Embedding-8B", + "size_b": 8, + "canonical_id": "qwen3-language-embedding", + "hf_private": false } - ] + ], + "lastUpdated": "2026-07-03T04:02:08.833Z" + }, + { + "name": "Nscale", + "url": "https://www.nscale.com/product/serverless", + "headquarters": "United Kingdom", + "region": "EEA Equivalent", + "gdpr_compliant": true, + "eu_endpoints": true, + "models": [] }, { "name": "Mistral AI", @@ -1891,25 +6395,6 @@ "gdpr_compliant": true, "eu_endpoints": true, "models": [ - { - "name": "Mistral Large 3", - "type": "chat", - "input_price_per_1m": 0.5, - "output_price_per_1m": 1.5, - "currency": "USD", - "api_endpoint": "mistral-large-latest", - "capabilities": [ - "tools" - ], - "size_b": 123, - "hf_private": false, - "ollama_id": "mistral-large", - "size_source": "manual", - "hf_id": "mistralai/Mistral-Large-Instruct-2407", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "mistral-large-3" - }, { "name": "Mistral Medium 3.5", "type": "chat", @@ -1943,6 +6428,69 @@ "hf_status": 200, "canonical_id": "mistral-small-4" }, + { + "name": "Mistral Large 3", + "type": "chat", + "input_price_per_1m": 0.5, + "output_price_per_1m": 1.5, + "currency": "USD", + "api_endpoint": "mistral-large-latest", + "capabilities": [ + "tools" + ], + "size_b": 123, + "hf_private": false, + "ollama_id": "mistral-large", + "size_source": "manual", + "hf_id": "mistralai/Mistral-Large-Instruct-2407", + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "mistral-large-3" + }, + { + "name": "Voxtral Mini Transcribe 2", + "type": "audio", + "currency": "USD", + "api_endpoint": "voxtral-mini-latest", + "hf_private": false, + "price_per_minute": 0.003, + "capabilities": [ + "audio" + ], + "size_b": 3, + "size_source": "manual", + "hf_id": "mistralai/Voxtral-Mini-3B-2507", + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "voxtral-mini-transcribe-2" + }, + { + "name": "Voxtral Mini Transcribe Realtime", + "type": "audio", + "currency": "USD", + "capabilities": [ + "audio" + ], + "price_per_minute": 0.006, + "canonical_id": "voxtral-mini-transcribe-realtime" + }, + { + "name": "Voxtral Small", + "type": "audio", + "currency": "USD", + "api_endpoint": "voxtral-small-latest", + "capabilities": [ + "audio" + ], + "size_b": 24, + "hf_id": "mistralai/Voxtral-Small-24B-2507", + "hf_private": false, + "size_source": "manual", + "hf_validated_at": "2026-03-22T19:23:09.981Z", + "hf_status": 200, + "canonical_id": "voxtral-small", + "price_per_minute": 0.1 + }, { "name": "Devstral 2", "type": "chat", @@ -1993,24 +6541,6 @@ "hf_private": true, "canonical_id": "codestral" }, - { - "name": "Mistral Small 3.2", - "type": "chat", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.3, - "currency": "USD", - "api_endpoint": "mistral-small-latest", - "capabilities": [ - "vision", - "tools" - ], - "size_b": 24, - "hf_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", - "hf_private": false, - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "mistral-small-3-2" - }, { "name": "Magistral Medium", "type": "chat", @@ -2019,7 +6549,10 @@ "currency": "USD", "api_endpoint": "magistral-medium-latest", "hf_private": true, - "canonical_id": "magistral-medium" + "canonical_id": "magistral-medium", + "capabilities": [ + "reasoning" + ] }, { "name": "Magistral Small", @@ -2034,7 +6567,10 @@ "hf_id": "mistralai/Magistral-Small-2506", "hf_validated_at": "2026-03-22T20:03:46.317Z", "hf_status": 200, - "canonical_id": "magistral-small" + "canonical_id": "magistral-small", + "capabilities": [ + "reasoning" + ] }, { "name": "Ministral 3 - 3B", @@ -2078,84 +6614,20 @@ "canonical_id": "ministral-3-14b" }, { - "name": "Voxtral Mini Transcribe 2", - "type": "audio", + "name": "Classifier API model 3B", + "type": "chat", + "input_price_per_1m": 0.1, + "output_price_per_1m": 0.1, "currency": "USD", - "api_endpoint": "voxtral-mini-latest", - "hf_private": false, - "price_per_minute": 0.003, - "capabilities": [ - "audio", - "tools" - ], "size_b": 3, - "size_source": "manual", - "hf_id": "mistralai/Voxtral-Mini-3B-2507", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "voxtral-mini-transcribe-2" - }, - { - "name": "Voxtral Realtime", - "type": "audio", - "currency": "USD", - "api_endpoint": "voxtral-mini-latest", - "hf_private": false, - "price_per_minute": 0.006, - "capabilities": [ - "audio", - "tools" - ], - "size_b": 4, - "size_source": "manual", - "hf_id": "mistralai/Voxtral-Mini-4B-Realtime-2602", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "voxtral-realtime" - }, - { - "name": "Voxtral Small", - "type": "audio", - "input_price_per_1m": 0.004, - "output_price_per_1m": 0.3, - "currency": "USD", - "api_endpoint": "voxtral-small-latest", - "capabilities": [ - "audio", - "tools" - ], - "size_b": 24, - "hf_id": "mistralai/Voxtral-Small-24B-2507", - "hf_private": false, - "size_source": "manual", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "voxtral-small" - }, - { - "name": "Voxtral Mini", - "type": "audio", - "input_price_per_1m": 0.001, - "output_price_per_1m": 0.04, - "currency": "USD", - "api_endpoint": "voxtral-mini-latest", "hf_private": false, - "capabilities": [ - "audio", - "tools" - ], - "size_b": 3, - "size_source": "manual", - "hf_id": "mistralai/Voxtral-Mini-3B-2507", - "hf_validated_at": "2026-03-22T19:23:09.981Z", - "hf_status": 200, - "canonical_id": "voxtral-mini" + "canonical_id": "classifier-api-model-3b" }, { "name": "Classifier API model 8B", "type": "chat", - "input_price_per_1m": 0.1, - "output_price_per_1m": 0.1, + "input_price_per_1m": 0.04, + "output_price_per_1m": 0.04, "currency": "USD", "size_b": 8, "hf_private": false, @@ -2171,16 +6643,6 @@ "hf_private": true, "canonical_id": "mistral-moderation" }, - { - "name": "Classifier API model 3B", - "type": "chat", - "input_price_per_1m": 0.04, - "output_price_per_1m": 0.04, - "currency": "USD", - "size_b": 3, - "hf_private": false, - "canonical_id": "classifier-api-model-3b" - }, { "name": "Codestral Embed", "type": "embedding", @@ -2218,8 +6680,27 @@ "hf_validated_at": "2026-03-22T19:23:09.981Z", "hf_status": 200, "canonical_id": "mistral-nemo" + }, + { + "name": "Mixtral 8x7B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 0.7, + "output_price_per_1m": 0.7, + "size_b": 7, + "canonical_id": "mixtral-8x7b" + }, + { + "name": "Mixtral 8x22B", + "type": "chat", + "currency": "USD", + "input_price_per_1m": 2, + "output_price_per_1m": 6, + "size_b": 22, + "canonical_id": "mixtral-8x22b" } - ] + ], + "lastUpdated": "2026-07-03T07:16:45.395Z" }, { "name": "OpenRouter", @@ -2819,7 +7300,7 @@ { "name": "deepseek/deepseek-v4-flash", "type": "chat", - "input_price_per_1m": 0.089, + "input_price_per_1m": 0.09, "output_price_per_1m": 0.18, "currency": "USD", "hf_id": "deepseek-ai/DeepSeek-V4-Flash", @@ -5368,8 +9849,8 @@ { "name": "z-ai/glm-5.1", "type": "chat", - "input_price_per_1m": 0.975, - "output_price_per_1m": 4.3, + "input_price_per_1m": 0.966, + "output_price_per_1m": 3.036, "currency": "USD", "hf_id": "zai-org/GLM-5.1", "capabilities": [