openapi: 3.1.0
info:
  title: Cerebras Inference API
  description: |
    OpenAI-compatible REST API for ultra-low-latency inference on open-weight
    large language models hosted on Cerebras wafer-scale silicon. Supports
    chat completions, text completions, and model discovery via Bearer
    token authentication. Generated as a best-effort spec from public
    Cerebras inference documentation; verify against the official API
    reference at https://inference-docs.cerebras.ai before production use.
  version: "1.0.0"
  contact:
    name: Cerebras Inference
    url: https://inference-docs.cerebras.ai
  license:
    name: Cerebras Terms of Service
    url: https://www.cerebras.ai/terms
servers:
  - url: https://api.cerebras.ai/v1
    description: Cerebras Inference Cloud
security:
  - bearerAuth: []
tags:
  - name: Chat
    description: OpenAI-compatible chat completions.
  - name: Completions
    description: Text completions.
  - name: Models
    description: Discover available models.
paths:
  /chat/completions:
    post:
      tags: [Chat]
      summary: Create a chat completion
      description: |
        Generates a model response for the given chat conversation. Supports
        streaming via server-sent events and tool/function calling. Drop-in
        compatible with the OpenAI client libraries.
      operationId: createChatCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion response.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                type: string
                description: Server-sent events stream of chat completion chunks.
        '400':
          $ref: '#/components/responses/ErrorResponse'
        '401':
          $ref: '#/components/responses/ErrorResponse'
        '429':
          $ref: '#/components/responses/ErrorResponse'
  /completions:
    post:
      tags: [Completions]
      summary: Create a text completion
      description: Generates a text completion for the given prompt.
      operationId: createCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CompletionRequest'
      responses:
        '200':
          description: Text completion response.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CompletionResponse'
        '400':
          $ref: '#/components/responses/ErrorResponse'
        '401':
          $ref: '#/components/responses/ErrorResponse'
        '429':
          $ref: '#/components/responses/ErrorResponse'
  /models:
    get:
      tags: [Models]
      summary: List available models
      description: Returns an array of models hosted on Cerebras Inference.
      operationId: listModels
      responses:
        '200':
          description: List of available models.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelList'
        '401':
          $ref: '#/components/responses/ErrorResponse'
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: Provision a CEREBRAS_API_KEY at https://cloud.cerebras.ai
  responses:
    ErrorResponse:
      description: Error response.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    ChatCompletionRequest:
      type: object
      required: [model, messages]
      properties:
        model:
          type: string
          description: Model identifier (e.g. llama3.1-8b, qwen-3-235b-a22b-instruct-2507, gpt-oss-120b).
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        temperature:
          type: number
          minimum: 0
          maximum: 1.5
        top_p:
          type: number
          minimum: 0
          maximum: 1
        max_completion_tokens:
          type: integer
        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
        logprobs:
          type: boolean
        top_logprobs:
          type: integer
        tools:
          type: array
          items:
            type: object
        tool_choice:
          oneOf:
            - type: string
            - type: object
        parallel_tool_calls:
          type: boolean
        response_format:
          type: object
        user:
          type: string
        reasoning_effort:
          type: string
    ChatMessage:
      type: object
      required: [role]
      properties:
        role:
          type: string
          enum: [system, user, assistant, developer, tool]
        content:
          oneOf:
            - type: string
            - type: array
              items:
                type: object
        name:
          type: string
        tool_call_id:
          type: string
        tool_calls:
          type: array
          items:
            type: object
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          example: chat.completion
        created:
          type: integer
        model:
          type: string
        system_fingerprint:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index: { type: integer }
              finish_reason:
                type: string
                enum: [stop, length, tool_calls, content_filter]
              message:
                $ref: '#/components/schemas/ChatMessage'
              logprobs:
                type: object
                nullable: true
        usage:
          $ref: '#/components/schemas/Usage'
        time_info:
          $ref: '#/components/schemas/TimeInfo'
    CompletionRequest:
      type: object
      required: [model]
      properties:
        model:
          type: string
        prompt:
          oneOf:
            - type: string
            - type: array
              items: { type: string }
        max_tokens:
          type: integer
        temperature:
          type: number
          minimum: 0
          maximum: 1.5
        top_p:
          type: number
          minimum: 0
          maximum: 1
        stream:
          type: boolean
        stop:
          oneOf:
            - type: string
            - type: array
              items: { type: string }
        seed:
          type: integer
        logprobs:
          type: integer
          minimum: 0
          maximum: 20
        echo:
          type: boolean
        user:
          type: string
    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
                enum: [stop, length, content_filter]
              logprobs:
                type: object
                nullable: true
        usage:
          $ref: '#/components/schemas/Usage'
        time_info:
          $ref: '#/components/schemas/TimeInfo'
    ModelList:
      type: object
      properties:
        object:
          type: string
          example: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Model'
    Model:
      type: object
      properties:
        id: { type: string }
        object: { type: string, example: model }
        created: { type: integer }
        owned_by: { type: string }
    Usage:
      type: object
      properties:
        prompt_tokens: { type: integer }
        completion_tokens: { type: integer }
        total_tokens: { type: integer }
    TimeInfo:
      type: object
      properties:
        queue_time: { type: number }
        prompt_time: { type: number }
        completion_time: { type: number }
        total_time: { type: number }
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            message: { type: string }
            type: { type: string }
            code: { type: string }
            param: { type: string }