Ollama Completions API

openapi: 3.1.0
info:
  title: Ollama Blobs Completions API
  description: Ollama provides a REST API for running and managing large language models locally. The API supports text generation, chat completions, embeddings, model management, and streaming responses. It serves as the primary interface for interacting with models running on the Ollama inference engine at localhost:11434.
  version: 0.1.0
  contact:
    name: Ollama Team
    url: https://ollama.com
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
  termsOfService: https://ollama.com/terms
servers:
- url: http://localhost:11434
  description: Local Ollama Server
tags:
- name: Completions
  description: Generate text completions using the OpenAI-compatible completions endpoint.
paths:
  /completions:
    post:
      operationId: createCompletion
      summary: Ollama Create completion
      description: Creates a completion for the provided prompt. Compatible with the OpenAI Completions API format. Supports streaming, JSON mode, and reproducible outputs.
      tags:
      - Completions
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CompletionRequest'
      responses:
        '200':
          description: Successful completion response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CompletionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/CompletionStreamResponse'
        '400':
          description: Bad Request
        '404':
          description: Model not found
components:
  schemas:
    CompletionStreamResponse:
      type: object
      description: A streaming text completion chunk.
      properties:
        id:
          type: string
          description: A unique identifier for the completion.
        object:
          type: string
          description: The object type.
        created:
          type: integer
          description: Unix timestamp of creation.
        model:
          type: string
          description: The model used.
        choices:
          type: array
          description: A list of completion chunk choices.
          items:
            type: object
            properties:
              index:
                type: integer
                description: The index of the choice.
              text:
                type: string
                description: The text delta.
              finish_reason:
                type:
                - string
                - 'null'
                description: The finish reason, if applicable.
    CompletionResponse:
      type: object
      description: Response object from a text completion request.
      properties:
        id:
          type: string
          description: A unique identifier for the completion.
        object:
          type: string
          description: The object type, always text_completion.
          const: text_completion
        created:
          type: integer
          description: Unix timestamp of when the completion was created.
        model:
          type: string
          description: The model used for the completion.
        choices:
          type: array
          description: A list of completion choices.
          items:
            type: object
            properties:
              index:
                type: integer
                description: The index of the choice.
              text:
                type: string
                description: The generated text.
              finish_reason:
                type: string
                description: The reason the model stopped generating.
                enum:
                - stop
                - length
        usage:
          $ref: '#/components/schemas/UsageStats'
    UsageStats:
      type: object
      description: Token usage statistics for the request.
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt.
        completion_tokens:
          type: integer
          description: Number of tokens in the generated completion.
        total_tokens:
          type: integer
          description: Total number of tokens used in the request.
    CompletionRequest:
      type: object
      description: Request body for creating a text completion in OpenAI-compatible format.
      required:
      - model
      - prompt
      properties:
        model:
          type: string
          description: The model to use for completion.
        prompt:
          description: The prompt to generate completions for.
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        temperature:
          type: number
          description: Sampling temperature between 0 and 2.
          minimum: 0.0
          maximum: 2.0
        top_p:
          type: number
          description: Nucleus sampling parameter.
          minimum: 0.0
          maximum: 1.0
        max_tokens:
          type: integer
          description: Maximum number of tokens to generate.
        frequency_penalty:
          type: number
          description: Penalty for token frequency.
          minimum: -2.0
          maximum: 2.0
        presence_penalty:
          type: number
          description: Penalty for token presence.
          minimum: -2.0
          maximum: 2.0
        seed:
          type: integer
          description: Random seed for deterministic generation.
        stop:
          description: Stop sequences for generation.
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        stream:
          type: boolean
          description: Whether to stream back partial progress.
          default: false
        stream_options:
          type: object
          description: Options for streaming responses.
          properties:
            include_usage:
              type: boolean
              description: If true, includes usage info in the stream.
        suffix:
          type: string
          description: The suffix that comes after the completion.
externalDocs:
  description: Ollama API Documentation
  url: https://docs.ollama.com/api/introduction