{"source":"https://models.dev/api.json","loaded_at":"2026-08-10T18:48:05.216Z","pricing":"provider-declared (per 1M tokens, USD); jishie-measured evals are a later step","total":34,"returned":34,"models":[{"key":"nebius/Qwen/Qwen3-Embedding-8B","model":"Qwen/Qwen3-Embedding-8B","name":"Qwen3-Embedding-8B","provider":"nebius","provider_name":"Nebius Token Factory","family":"text-embedding","input_per_mtok":0.01,"output_per_mtok":0,"cache_read_per_mtok":null,"context":32768,"max_output":0,"modalities":["text"],"tool_call":false,"reasoning":false},{"key":"nebius/nvidia/Nemotron-3-Nano-Omni","model":"nvidia/Nemotron-3-Nano-Omni","name":"Nemotron-3-Nano-Omni","provider":"nebius","provider_name":"Nebius Token Factory","family":"nemotron","input_per_mtok":0.06,"output_per_mtok":0.24,"cache_read_per_mtok":0.006,"context":65536,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","model":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","name":"Nemotron-3-Nano-30B-A3B","provider":"nebius","provider_name":"Nebius Token Factory","family":"nemotron","input_per_mtok":0.06,"output_per_mtok":0.24,"cache_read_per_mtok":0.006,"context":32000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/google/gemma-3-27b-it","model":"google/gemma-3-27b-it","name":"Gemma-3-27b-it","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.1,"output_per_mtok":0.3,"cache_read_per_mtok":0.01,"context":110000,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","model":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3-30B-A3B-Instruct-2507","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.1,"output_per_mtok":0.3,"cache_read_per_mtok":0.01,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/Qwen/Qwen3-32B","model":"Qwen/Qwen3-32B","name":"Qwen3-32B","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.1,"output_per_mtok":0.3,"cache_read_per_mtok":0.01,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/deepseek-ai/DeepSeek-V4-Flash","model":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","provider":"nebius","provider_name":"Nebius Token Factory","family":"deepseek-flash","input_per_mtok":0.14,"output_per_mtok":0.28,"cache_read_per_mtok":0.14,"context":131072,"max_output":131072,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/NousResearch/Hermes-4-70B","model":"NousResearch/Hermes-4-70B","name":"Hermes-4-70B","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.13,"output_per_mtok":0.4,"cache_read_per_mtok":0.013,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/meta-llama/Llama-3.3-70B-Instruct","model":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.13,"output_per_mtok":0.4,"cache_read_per_mtok":0.013,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/openai/gpt-oss-120b-fast","model":"openai/gpt-oss-120b-fast","name":"gpt-oss-120b-fast","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.1,"output_per_mtok":0.5,"cache_read_per_mtok":0.01,"context":8000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/openai/gpt-oss-120b","model":"openai/gpt-oss-120b","name":"gpt-oss-120b","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.15,"output_per_mtok":0.6,"cache_read_per_mtok":0.015,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","model":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","provider":"nebius","provider_name":"Nebius Token Factory","family":"qwen","input_per_mtok":0.2,"output_per_mtok":0.6,"cache_read_per_mtok":null,"context":262144,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/deepseek-ai/DeepSeek-V3.2","model":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.3,"output_per_mtok":0.45,"cache_read_per_mtok":0.03,"context":163000,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/Qwen/Qwen2.5-VL-72B-Instruct","model":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen2.5-VL-72B-Instruct","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.25,"output_per_mtok":0.75,"cache_read_per_mtok":0.025,"context":128000,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":false},{"key":"nebius/Qwen/Qwen3-Next-80B-A3B-Thinking-fast","model":"Qwen/Qwen3-Next-80B-A3B-Thinking-fast","name":"Qwen3-Next-80B-A3B-Thinking-fast","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.15,"output_per_mtok":1.2,"cache_read_per_mtok":0.015,"context":8000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/Qwen/Qwen3-Next-80B-A3B-Thinking","model":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next-80B-A3B-Thinking","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.15,"output_per_mtok":1.2,"cache_read_per_mtok":0.015,"context":128000,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/PrimeIntellect/INTELLECT-3","model":"PrimeIntellect/INTELLECT-3","name":"INTELLECT-3","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.2,"output_per_mtok":1.1,"cache_read_per_mtok":0.02,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/nvidia/nemotron-3-super-120b-a12b","model":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron-3-Super-120B-A12B","provider":"nebius","provider_name":"Nebius Token Factory","family":"nemotron","input_per_mtok":0.3,"output_per_mtok":0.9,"cache_read_per_mtok":null,"context":256000,"max_output":32768,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/MiniMaxAI/MiniMax-M2.5-fast","model":"MiniMaxAI/MiniMax-M2.5-fast","name":"MiniMax-M2.5-fast","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.3,"output_per_mtok":1.2,"cache_read_per_mtok":0.03,"context":8000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/MiniMaxAI/MiniMax-M2.5","model":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.3,"output_per_mtok":1.2,"cache_read_per_mtok":0.03,"context":196608,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/MiniMaxAI/MiniMax-M3","model":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","provider":"nebius","provider_name":"Nebius Token Factory","family":"minimax","input_per_mtok":0.3,"output_per_mtok":1.2,"cache_read_per_mtok":null,"context":1048576,"max_output":1048576,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/deepseek-ai/DeepSeek-V3.2-fast","model":"deepseek-ai/DeepSeek-V3.2-fast","name":"DeepSeek-V3.2-fast","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.4,"output_per_mtok":2,"cache_read_per_mtok":0.04,"context":8000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/Qwen/Qwen3-235B-A22B-Thinking-2507-fast","model":"Qwen/Qwen3-235B-A22B-Thinking-2507-fast","name":"Qwen3-235B-A22B-Thinking-2507-fast","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.5,"output_per_mtok":2,"cache_read_per_mtok":0.05,"context":8000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","model":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","name":"Llama-3.1-Nemotron-Ultra-253B-v1","provider":"nebius","provider_name":"Nebius Token Factory","family":"nemotron","input_per_mtok":0.6,"output_per_mtok":1.8,"cache_read_per_mtok":0.06,"context":128000,"max_output":4096,"modalities":["text"],"tool_call":true,"reasoning":false},{"key":"nebius/moonshotai/Kimi-K2.5-fast","model":"moonshotai/Kimi-K2.5-fast","name":"Kimi-K2.5-fast","provider":"nebius","provider_name":"Nebius Token Factory","family":"kimi-k2","input_per_mtok":0.5,"output_per_mtok":2.5,"cache_read_per_mtok":0.05,"context":256000,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nebius/moonshotai/Kimi-K2.5","model":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","provider":"nebius","provider_name":"Nebius Token Factory","family":"kimi-k2","input_per_mtok":0.5,"output_per_mtok":2.5,"cache_read_per_mtok":0.05,"context":256000,"max_output":8192,"modalities":["text","image"],"tool_call":true,"reasoning":true},{"key":"nebius/Qwen/Qwen3.5-397B-A17B","model":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.6,"output_per_mtok":3.6,"cache_read_per_mtok":0.06,"context":262144,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/Qwen/Qwen3.5-397B-A17B-fast","model":"Qwen/Qwen3.5-397B-A17B-fast","name":"Qwen3.5-397B-A17B-fast","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":0.6,"output_per_mtok":3.6,"cache_read_per_mtok":0.06,"context":8000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/NousResearch/Hermes-4-405B","model":"NousResearch/Hermes-4-405B","name":"Hermes-4-405B","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":1,"output_per_mtok":3,"cache_read_per_mtok":0.1,"context":128000,"max_output":8192,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/zai-org/GLM-5","model":"zai-org/GLM-5","name":"GLM-5","provider":"nebius","provider_name":"Nebius Token Factory","input_per_mtok":1,"output_per_mtok":3.2,"cache_read_per_mtok":0.1,"context":200000,"max_output":16384,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/moonshotai/Kimi-K2.7-Code","model":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","provider":"nebius","provider_name":"Nebius Token Factory","family":"kimi-k2","input_per_mtok":0.95,"output_per_mtok":4,"cache_read_per_mtok":null,"context":262144,"max_output":8000,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/zai-org/GLM-5.2","model":"zai-org/GLM-5.2","name":"GLM-5.2","provider":"nebius","provider_name":"Nebius Token Factory","family":"glm","input_per_mtok":1.4,"output_per_mtok":4.4,"cache_read_per_mtok":null,"context":432000,"max_output":432000,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/deepseek-ai/DeepSeek-V4-Pro","model":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","provider":"nebius","provider_name":"Nebius Token Factory","family":"deepseek-thinking","input_per_mtok":1.75,"output_per_mtok":3.5,"cache_read_per_mtok":0.15,"context":1000000,"max_output":384000,"modalities":["text"],"tool_call":true,"reasoning":true},{"key":"nebius/moonshotai/Kimi-K3","model":"moonshotai/Kimi-K3","name":"Kimi K3","provider":"nebius","provider_name":"Nebius Token Factory","family":"kimi-k3","input_per_mtok":3,"output_per_mtok":15,"cache_read_per_mtok":3,"context":1048576,"max_output":8000,"modalities":["text"],"tool_call":true,"reasoning":true}]}