NVIDIA NIM Chat API

openapi: 3.1.0
info:
  title: NVIDIA NIM Biology (BioNeMo) ASR Chat API
  description: 'NVIDIA BioNeMo NIMs for drug discovery and structural biology. Each model is a containerized microservice with its own task-specific payload but a consistent JSON contract. Includes protein structure prediction (AlphaFold2, ESMFold, OpenFold), protein generation (ProtGPT2, RFDiffusion), molecular property prediction (MolMIM), small molecule generation, and molecular docking (DiffDock).

    '
  version: '2026-05-25'
  contact:
    name: NVIDIA Developer Support
    url: https://forums.developer.nvidia.com/c/ai-data-science/nemo-llm-service/
  license:
    name: NVIDIA AI Enterprise License
    url: https://www.nvidia.com/en-us/data-center/products/ai-enterprise/
servers:
- url: https://integrate.api.nvidia.com
  description: NVIDIA-hosted NIM endpoint
- url: http://localhost:8000
  description: Self-hosted NIM container default
security:
- BearerAuth: []
tags:
- name: Chat
  description: OpenAI-compatible chat completion operations
paths:
  /v1/chat/completions:
    post:
      summary: Create A Chat Completion
      description: 'Generate a chat completion for the supplied messages. Compatible with the OpenAI chat completions schema; supports streaming via Server-Sent Events when `stream: true` is set, tool/function calling, JSON-mode structured outputs, and (on VLM models) image inputs inside the messages array.

        '
      operationId: createChatCompletion
      tags:
      - Chat
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion response (or SSE stream when stream=true).
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                type: string
                description: 'SSE stream of `data:` JSON deltas terminated by `data: [DONE]`.'
        '400':
          description: Invalid request.
        '401':
          description: Missing or invalid API key.
        '403':
          description: API key lacks access to the requested model.
        '404':
          description: Requested model not found in this endpoint's catalog.
        '429':
          description: Rate limit or quota exceeded.
        '500':
          description: Upstream inference error.
components:
  schemas:
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          description: Model identifier (e.g. `meta/llama-3.3-70b-instruct`, `nvidia/llama-3.1-nemotron-70b-instruct`).
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 0.2
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 0.7
        max_tokens:
          type: integer
          minimum: 1
          default: 1024
        stream:
          type: boolean
          default: false
        stop:
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        n:
          type: integer
          minimum: 1
          default: 1
        seed:
          type: integer
        tools:
          type: array
          items:
            $ref: '#/components/schemas/Tool'
        tool_choice:
          oneOf:
          - type: string
            enum:
            - auto
            - none
            - required
          - type: object
        response_format:
          type: object
          properties:
            type:
              type: string
              enum:
              - text
              - json_object
              - json_schema
            json_schema:
              type: object
        frequency_penalty:
          type: number
        presence_penalty:
          type: number
    ChatMessage:
      type: object
      required:
      - role
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
        content:
          oneOf:
          - type: string
          - type: array
            items:
              $ref: '#/components/schemas/ContentPart'
        name:
          type: string
        tool_calls:
          type: array
          items:
            $ref: '#/components/schemas/ToolCall'
        tool_call_id:
          type: string
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                $ref: '#/components/schemas/ChatMessage'
              finish_reason:
                type: string
                enum:
                - stop
                - length
                - tool_calls
                - content_filter
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            completion_tokens:
              type: integer
            total_tokens:
              type: integer
    ContentPart:
      type: object
      required:
      - type
      properties:
        type:
          type: string
          enum:
          - text
          - image_url
        text:
          type: string
        image_url:
          type: object
          properties:
            url:
              type: string
              description: HTTPS URL or `data:image/...;base64,...` payload.
    Tool:
      type: object
      required:
      - type
      - function
      properties:
        type:
          type: string
          enum:
          - function
        function:
          type: object
          required:
          - name
          properties:
            name:
              type: string
            description:
              type: string
            parameters:
              type: object
    ToolCall:
      type: object
      properties:
        id:
          type: string
        type:
          type: string
          enum:
          - function
        function:
          type: object
          properties:
            name:
              type: string
            arguments:
              type: string
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: nvapi-...