openapi: 3.1.0
info:
  title: DeepInfra Inference API
  description: >-
    OpenAI-compatible inference API for DeepInfra's 100+ open-source models.
    Covers chat completions, text completions, embeddings, audio
    (transcriptions, translations, text-to-speech), image generation, and
    model listing. Authenticated with a Bearer API token.
  version: "1.0.0"
servers:
  - url: https://api.deepinfra.com/v1/openai
    description: OpenAI-compatible base URL
  - url: https://api.deepinfra.com
    description: DeepInfra native base URL
security:
  - bearerAuth: []
tags:
  - name: Chat
  - name: Completions
  - name: Embeddings
  - name: Audio
  - name: Images
  - name: Models
paths:
  /chat/completions:
    post:
      tags: [Chat]
      summary: Create a chat completion (OpenAI-compatible)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, messages]
              properties:
                model: { type: string }
                messages:
                  type: array
                  items:
                    type: object
                    properties:
                      role: { type: string, enum: [system, user, assistant, tool] }
                      content: { type: string }
                temperature: { type: number }
                top_p: { type: number }
                max_tokens: { type: integer }
                stream: { type: boolean }
                tools:
                  type: array
                  items: { type: object }
                response_format: { type: object }
      responses:
        '200':
          description: Chat completion result
          content:
            application/json:
              schema: { type: object }
  /completions:
    post:
      tags: [Completions]
      summary: Create a text completion (legacy, OpenAI-compatible)
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model: { type: string }
                prompt:
                  oneOf:
                    - { type: string }
                    - { type: array, items: { type: string } }
                max_tokens: { type: integer }
                temperature: { type: number }
                stream: { type: boolean }
      responses:
        '200':
          description: Completion result
          content:
            application/json:
              schema: { type: object }
  /embeddings:
    post:
      tags: [Embeddings]
      summary: Create embeddings for input text
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, input]
              properties:
                model: { type: string }
                input:
                  oneOf:
                    - { type: string }
                    - { type: array, items: { type: string } }
                encoding_format:
                  type: string
                  enum: [float, base64]
      responses:
        '200':
          description: Embeddings
          content:
            application/json:
              schema: { type: object }
  /audio/transcriptions:
    post:
      tags: [Audio]
      summary: Transcribe audio to text (Whisper)
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [file, model]
              properties:
                file: { type: string, format: binary }
                model: { type: string }
                language: { type: string }
                prompt: { type: string }
                response_format:
                  type: string
                  enum: [json, text, srt, verbose_json, vtt]
                temperature: { type: number }
      responses:
        '200':
          description: Transcription
          content:
            application/json:
              schema: { type: object }
  /audio/translations:
    post:
      tags: [Audio]
      summary: Translate audio into English text
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [file, model]
              properties:
                file: { type: string, format: binary }
                model: { type: string }
                prompt: { type: string }
                response_format: { type: string }
                temperature: { type: number }
      responses:
        '200':
          description: Translation
          content:
            application/json:
              schema: { type: object }
  /audio/speech:
    post:
      tags: [Audio]
      summary: Synthesize text to speech
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, input]
              properties:
                model: { type: string }
                input: { type: string }
                voice: { type: string }
                response_format:
                  type: string
                  enum: [mp3, opus, aac, flac, wav, pcm]
                speed: { type: number }
      responses:
        '200':
          description: Audio bytes
          content:
            audio/mpeg: {}
            audio/wav: {}
  /images/generations:
    post:
      tags: [Images]
      summary: Generate images from a prompt
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [model, prompt]
              properties:
                model: { type: string }
                prompt: { type: string }
                n: { type: integer }
                size: { type: string }
                response_format:
                  type: string
                  enum: [url, b64_json]
      responses:
        '200':
          description: Generated images
          content:
            application/json:
              schema: { type: object }
  /models:
    get:
      tags: [Models]
      summary: List available models
      responses:
        '200':
          description: Models
          content:
            application/json:
              schema: { type: object }
  /models/{model}:
    get:
      tags: [Models]
      summary: Get metadata for a model
      parameters:
        - in: path
          name: model
          required: true
          schema: { type: string }
      responses:
        '200':
          description: Model
          content:
            application/json:
              schema: { type: object }
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: DeepInfra API token (DEEPINFRA_TOKEN) sent as a Bearer token.