NVIDIA NIM Completions API

openapi: 3.1.0
info:
  title: NVIDIA NIM Completions API
  description: >
    Legacy OpenAI-compatible text completion endpoint. Accepts a raw prompt
    (instead of a structured messages array) and returns generated text. Same
    streaming, stop, and sampling controls as the chat endpoint.
  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: Completions
    description: Legacy text completion operations
paths:
  /v1/completions:
    post:
      summary: Create A Text Completion
      description: Generate a text completion from a raw prompt against a supported NIM-served model.
      operationId: createCompletion
      tags:
        - Completions
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CompletionRequest'
      responses:
        '200':
          description: Completion response (or SSE stream when stream=true).
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CompletionResponse'
        '400':
          description: Invalid request.
        '401':
          description: Missing or invalid API key.
        '429':
          description: Rate limit exceeded.
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: nvapi-...
  schemas:
    CompletionRequest:
      type: object
      required: [model, prompt]
      properties:
        model:
          type: string
        prompt:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        max_tokens:
          type: integer
          default: 1024
        temperature:
          type: number
          default: 0.2
        top_p:
          type: number
          default: 0.7
        n:
          type: integer
          default: 1
        stream:
          type: boolean
          default: false
        stop:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        seed:
          type: integer
        frequency_penalty:
          type: number
        presence_penalty:
          type: number
        echo:
          type: boolean
        logprobs:
          type: integer
    CompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: text_completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              text:
                type: string
              index:
                type: integer
              finish_reason:
                type: string
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            completion_tokens:
              type: integer
            total_tokens:
              type: integer