ragflow/conf/models/nvidia.json

{
  "name": "NVIDIA",
  "url": {
    "default": "https://integrate.api.nvidia.com/v1"
  },
  "url_suffix": {
    "chat": "chat/completions",
    "models": "models",
    "embedding": "embeddings",
    "rerank": "ranking"
  },
  "class": "nvidia",
  "models": [
    {
      "name": "abacusai/dracarys-llama-3.1-70b-instruct",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "bytedance/seed-oss-36b-instruct",
      "max_tokens": 32768,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "deepseek-ai/deepseek-v4-flash",
      "max_tokens": 1048576,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "deepseek-ai/deepseek-v4-pro",
      "max_tokens": 1048576,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nv-embed-v1",
      "max_tokens": 8192,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "google/codegemma-7b",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "google/gemma-2-2b-it",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "google/gemma-4-31b-it",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "meta/llama-3.2-90b-vision-instruct",
      "max_tokens": 131072,
      "model_types": [
        "chat",
        "vision"
      ]
    },
    {
      "name": "meta/llama-4-maverick-17b-128e-instruct",
      "max_tokens": 1048576,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "minimaxai/minimax-m2.5",
      "max_tokens": 204800,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "minimaxai/minimax-m2.7",
      "max_tokens": 204800,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "mistralai/mistral-7b-instruct-v0.3",
      "max_tokens": 32768,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "mistralai/mistral-large-3-675b-instruct-2512",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "mistralai/mistral-medium-3.5-128b",
      "max_tokens": 131072,
      "model_types": [
        "chat",
        "vision"
      ]
    },
    {
      "name": "mistralai/mistral-nemotron",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "moonshotai/kimi-k2.6",
      "max_tokens": 262144,
      "model_types": [
        "chat",
        "vision"
      ]
    },
    {
      "name": "moonshotai/kimi-k2-instruct",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "moonshotai/kimi-k2-thinking",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "nvidia/gliner-pii",
      "max_tokens": 4096,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemoguard-8b-content-safety",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemoguard-8b-topic-control",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemotron-nano-8b-v1",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1",
      "max_tokens": 8192,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/llama-3.3-nemotron-super-49b-v1",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "nvidia/nemotron-3-nano-30b-a3b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
      "max_tokens": 131072,
      "model_types": [
        "chat",
        "vision"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "nvidia/nemotron-3-super-120b-a12b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nemotron-content-safety-reasoning-4b",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nemotron-mini-4b-instruct",
      "max_tokens": 4096,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nv-embed-v1",
      "max_tokens": 32768,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/nv-embedqa-e5-v5",
      "max_tokens": 512,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/nv-embedqa-mistral-7b-v2",
      "max_tokens": 512,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/nv-rerankqa-mistral-4b-v3",
      "max_tokens": 4096,
      "model_types": [
        "rerank"
      ]
    },
    {
      "name": "nvidia/llama-3.2-nv-rerankqa-1b-v2",
      "max_tokens": 4096,
      "model_types": [
        "rerank"
      ]
    },
    {
      "name": "nvidia/nvidia-nemotron-nano-9b-v2",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/riva-translate-4b-instruct-v1.1",
      "max_tokens": 4096,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "openai/gpt-oss-120b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "qwen/qwen3.5-122b-a10b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "qwen/qwen3-coder-480b-a35b-instruct",
      "max_tokens": 262144,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "z-ai/glm5",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "z-ai/glm-5.1",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    },
    {
      "name": "z-ai/glm4.7",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      }
    }
  ]
}