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": "deepseek-ai/deepseek-v4-flash",
      "max_tokens": 1048576,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "deepseek-ai/deepseek-v4-pro",
      "max_tokens": 1048576,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "google/diffusiongemma-26b-a4b-it",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "google/gemma-4-31b-it",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "meta/llama-3.1-70b-instruct",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "meta/llama-3.1-8b-instruct",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "meta/llama-3.2-11b-vision-instruct",
      "max_tokens": 8192,
      "model_types": [
        "chat",
        "vision"
      ]
    },
    {
      "name": "meta/llama-3.2-1b-instruct",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "meta/llama-3.2-3b-instruct",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "meta/llama-3.2-90b-vision-instruct",
      "max_tokens": 131072,
      "model_types": [
        "chat",
        "vision"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "meta/llama-3.3-70b-instruct",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "meta/llama-guard-4-12b",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "minimaxai/minimax-m3",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "mistralai/mistral-medium-3.5-128b",
      "max_tokens": 131072,
      "model_types": [
        "chat",
        "vision"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "mistralai/mistral-nemotron",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "moonshotai/kimi-k2.6",
      "max_tokens": 262144,
      "model_types": [
        "chat",
        "vision"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/ising-calibration-1.5-31b",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemotron-nano-8b-v1",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1",
      "max_tokens": 8192,
      "model_types": [
        "chat",
        "vision"
      ]
    },
    {
      "name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/llama-3.3-nemotron-super-49b-v1",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      },
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/nemotron-3-embed-1b",
      "max_tokens": 8192,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/nemotron-3-nano-30b-a3b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
      "max_tokens": 131072,
      "model_types": [
        "chat",
        "vision"
      ],
      "thinking": {
        "default_value": true,
        "clear_thinking": true
      },
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/nemotron-3-super-120b-a12b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/nemotron-3-ultra-550b-a55b",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nemotron-3.5-content-safety",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "nvidia/nemotron-mini-4b-instruct",
      "max_tokens": 4096,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/nemotron-nano-12b-v2-vl",
      "max_tokens": 8192,
      "model_types": [
        "chat",
        "vision"
      ]
    },
    {
      "name": "nvidia/nv-embed-v1",
      "max_tokens": 32768,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/nv-embedcode-7b-v1",
      "max_tokens": 8192,
      "model_types": [
        "embedding"
      ]
    },
    {
      "name": "nvidia/nvidia-nemotron-nano-9b-v2",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "nvidia/riva-translate-4b-instruct-v2",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "openai/gpt-oss-120b",
      "max_tokens": 131072,
      "model_types": [
        "chat"
      ],
      "tools": {
        "support": true
      }
    },
    {
      "name": "openai/gpt-oss-20b",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "poolside/laguna-xs-2.1",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "stepfun-ai/step-3.7-flash",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "thinkingmachines/inkling",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    },
    {
      "name": "z-ai/glm-5.2",
      "max_tokens": 8192,
      "model_types": [
        "chat"
      ]
    }
  ]
}