{
"meta/llama-3.1-70b-instruct": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 128000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "meta/llama-3.1-70b-instruct",
"input": ["text"],
"maxTokens": 4096,
"name": "Llama 3.1 70b Instruct",
"provider": "nvidia",
"reasoning": false
},
"meta/llama-3.1-8b-instruct": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 16000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "meta/llama-3.1-8b-instruct",
"input": ["text"],
"maxTokens": 4096,
"name": "Llama 3.1 8B Instruct",
"provider": "nvidia",
"reasoning": false
},
"meta/llama-3.2-11b-vision-instruct": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 128000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "meta/llama-3.2-11b-vision-instruct",
"input": ["text", "image"],
"maxTokens": 4096,
"name": "Llama 3.2 11b Vision Instruct",
"provider": "nvidia",
"reasoning": false
},
"meta/llama-3.2-90b-vision-instruct": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 128000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "meta/llama-3.2-90b-vision-instruct",
"input": ["text", "image"],
"maxTokens": 8192,
"name": "Llama-3.2-90B-Vision-Instruct",
"provider": "nvidia",
"reasoning": false
},
"meta/llama-3.3-70b-instruct": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 128000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "meta/llama-3.3-70b-instruct",
"input": ["text"],
"maxTokens": 4096,
"name": "Llama 3.3 70b Instruct",
"provider": "nvidia",
"reasoning": false
},
"minimaxai/minimax-m3": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 1000000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "minimaxai/minimax-m3",
"input": ["text", "image"],
"maxTokens": 16384,
"name": "MiniMax-M3",
"provider": "nvidia",
"reasoning": true
},
"mistralai/mistral-large-3-675b-instruct-2512": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "mistralai/mistral-large-3-675b-instruct-2512",
"input": ["text", "image"],
"maxTokens": 262144,
"name": "Mistral Large 3 675B Instruct 2512",
"provider": "nvidia",
"reasoning": false
},
"mistralai/mistral-small-4-119b-2603": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 128000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "mistralai/mistral-small-4-119b-2603",
"input": ["text", "image"],
"maxTokens": 8192,
"name": "mistral-small-4-119b-2603",
"provider": "nvidia",
"reasoning": true
},
"moonshotai/kimi-k2.6": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "moonshotai/kimi-k2.6",
"input": ["text", "image"],
"maxTokens": 262144,
"name": "Kimi K2.6",
"provider": "nvidia",
"reasoning": true
},
"nvidia/nemotron-3-nano-30b-a3b": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 131072,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "nvidia/nemotron-3-nano-30b-a3b",
"input": ["text"],
"maxTokens": 131072,
"name": "nemotron-3-nano-30b-a3b",
"provider": "nvidia",
"reasoning": true
},
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 256000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
"input": ["text", "image"],
"maxTokens": 65536,
"name": "Nemotron 3 Nano Omni",
"provider": "nvidia",
"reasoning": true
},
"nvidia/nemotron-3-super-120b-a12b": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0.2,
"output": 0.8
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "nvidia/nemotron-3-super-120b-a12b",
"input": ["text"],
"maxTokens": 262144,
"name": "Nemotron 3 Super",
"provider": "nvidia",
"reasoning": true
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 1000000,
"cost": {
"cacheRead": 0.15,
"cacheWrite": 0,
"input": 0.5,
"output": 2.5
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"input": ["text"],
"maxTokens": 65536,
"name": "Nemotron 3 Ultra 550B A55B",
"provider": "nvidia",
"reasoning": true
},
"nvidia/nvidia-nemotron-nano-9b-v2": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 131072,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "nvidia/nvidia-nemotron-nano-9b-v2",
"input": ["text"],
"maxTokens": 131072,
"name": "nvidia-nemotron-nano-9b-v2",
"provider": "nvidia",
"reasoning": true
},
"openai/gpt-oss-120b": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 128000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "openai/gpt-oss-120b",
"input": ["text"],
"maxTokens": 8192,
"name": "GPT-OSS-120B",
"provider": "nvidia",
"reasoning": true
},
"openai/gpt-oss-20b": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 131072,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "openai/gpt-oss-20b",
"input": ["text"],
"maxTokens": 32768,
"name": "GPT OSS 20B",
"provider": "nvidia",
"reasoning": true
},
"qwen/qwen3.5-122b-a10b": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 262144,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "qwen/qwen3.5-122b-a10b",
"input": ["text", "image"],
"maxTokens": 65536,
"name": "Qwen3.5 122B-A10B",
"provider": "nvidia",
"reasoning": true
},
"stepfun-ai/step-3.5-flash": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 256000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "stepfun-ai/step-3.5-flash",
"input": ["text"],
"maxTokens": 16384,
"name": "Step 3.5 Flash",
"provider": "nvidia",
"reasoning": true
},
"stepfun-ai/step-3.7-flash": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 256000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "stepfun-ai/step-3.7-flash",
"input": ["text", "image"],
"maxTokens": 16384,
"name": "Step 3.7 Flash",
"provider": "nvidia",
"reasoning": true
},
"z-ai/glm-5.2": {
"api": "openai-completions",
"baseUrl": "https://integrate.api.nvidia.com/v1",
"compat": {
"maxTokensField": "max_tokens",
"supportsDeveloperRole": false,
"supportsLongCacheRetention": false,
"supportsReasoningEffort": false,
"supportsStore": false,
"supportsStrictMode": false
},
"contextWindow": 1000000,
"cost": {
"cacheRead": 0,
"cacheWrite": 0,
"input": 0,
"output": 0
},
"headers": {
"NVCF-POLL-SECONDS": "3600"
},
"id": "z-ai/glm-5.2",
"input": ["text"],
"maxTokens": 131072,
"name": "GLM-5.2",
"provider": "nvidia",
"reasoning": true
}
}