Fastino Labs openai-compat API

OpenAI-compatible endpoints. Use with the OpenAI SDK by setting base_url=https://api.pioneer.ai/v1.
Documentation GitHub OpenAPI
OpenAPI Specification

openapi: 3.1.0
info:
  title: Pioneer Inference anthropic-compat openai-compat API
  version: 1.0.0
  description: Public inference API for Pioneer AI. Covers the Pioneer-native endpoint, OpenAI-compatible endpoints (/v1/chat/completions, /v1/completions, /v1/models), the Anthropic-compatible endpoint (/v1/messages), and inference history. Authenticate with an X-API-Key header (keys begin with pio_sk_).
  contact:
    name: Pioneer AI
    url: https://docs.pioneer.ai
    email: support@pioneer.ai
servers:
- url: https://api.pioneer.ai
  description: Production
security:
- ApiKeyAuth: []
- BearerAuth: []
tags:
- name: openai-compat
  description: OpenAI-compatible endpoints. Use with the OpenAI SDK by setting base_url=https://api.pioneer.ai/v1.
paths:
  /v1/chat/completions:
    post:
      operationId: create_chat_completion
      summary: Chat completions (OpenAI-compatible)
      description: OpenAI-compatible chat completions endpoint. Works with the OpenAI Python SDK by setting `base_url="https://api.pioneer.ai/v1"`. Set `stream=true` for SSE streaming. The response includes a `x_pioneer` extension field with `inference_id` and `routed_model`.
      tags:
      - openai-compat
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
            examples:
              simple:
                summary: Simple chat completion
                value:
                  model: Qwen/Qwen3-8B
                  messages:
                  - role: user
                    content: Hello!
              streaming:
                summary: Streaming chat completion
                value:
                  model: Qwen/Qwen3-8B
                  messages:
                  - role: user
                    content: Tell me a short story.
                  stream: true
                  max_tokens: 512
              pioneer_auto:
                summary: Use pioneer/auto router
                value:
                  model: pioneer/auto
                  messages:
                  - role: user
                    content: Classify this text.
      responses:
        '200':
          description: 'Chat completion result. Returns `application/json` when `stream=false` (default) and `text/event-stream` SSE when `stream=true`. Each SSE event is `data: {...}\n\n` terminated by `data: [DONE]\n\n`.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ChatCompletionStreamChunk'
              example: 'data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":0,"model":"Qwen/Qwen3-8B","choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}]}


                data: [DONE]


                '
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '404':
          $ref: '#/components/responses/ModelNotFound'
        '422':
          $ref: '#/components/responses/ValidationError'
        '429':
          $ref: '#/components/responses/RateLimited'
  /v1/completions:
    post:
      operationId: create_text_completion
      summary: Text completions (OpenAI-compatible)
      description: OpenAI-compatible legacy text completions endpoint. Accepts a `prompt` string and returns a completion. Set `stream=true` for SSE streaming.
      tags:
      - openai-compat
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TextCompletionRequest'
            examples:
              simple:
                summary: Simple text completion
                value:
                  model: Qwen/Qwen3-8B-Base
                  prompt: The capital of France is
                  max_tokens: 32
      responses:
        '200':
          description: Text completion result. `application/json` when `stream=false`, `text/event-stream` SSE when `stream=true`.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TextCompletionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/TextCompletionStreamChunk'
              example: 'data: {"id":"cmpl-abc","object":"text_completion","created":0,"model":"Qwen/Qwen3-8B-Base","choices":[{"index":0,"text":" Paris.","finish_reason":"stop"}]}


                data: [DONE]


                '
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '404':
          $ref: '#/components/responses/ModelNotFound'
        '422':
          $ref: '#/components/responses/ValidationError'
        '429':
          $ref: '#/components/responses/RateLimited'
components:
  responses:
    RateLimited:
      description: Rate limit exceeded. Retry after the duration in the `Retry-After` response header.
      headers:
        Retry-After:
          schema:
            type: integer
          description: Seconds to wait before retrying.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    PaymentRequired:
      description: Insufficient credits or no active billing plan.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    ValidationError:
      description: Request body failed schema validation.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ValidationErrorResponse'
    ModelNotFound:
      description: Model ID not found or not yet deployed.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  schemas:
    TextCompletionRequest:
      type: object
      required:
      - model
      - prompt
      properties:
        model:
          type: string
        prompt:
          type: string
        temperature:
          type: number
        max_tokens:
          type: integer
          minimum: 1
          maximum: 131072
        stream:
          type: boolean
        stop:
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        echo:
          type: boolean
          default: false
        logprobs:
          type: integer
          minimum: 0
          maximum: 20
        store:
          type: boolean
          default: true
        reasoning:
          type: object
    UsageStats:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
        prompt_tokens_details:
          type: object
          properties:
            cached_tokens:
              type: integer
              description: Input tokens served from cache (cache read).
            cache_write_tokens:
              type: integer
              description: Input tokens written to cache (cache creation).
    ValidationErrorResponse:
      type: object
      properties:
        detail:
          type: array
          items:
            type: object
            properties:
              loc:
                type: array
                items:
                  oneOf:
                  - type: string
                  - type: integer
              msg:
                type: string
              type:
                type: string
    TextCompletionResponse:
      type: object
      required:
      - id
      - object
      - created
      - model
      - choices
      - usage
      properties:
        id:
          type: string
        object:
          type: string
          enum:
          - text_completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              text:
                type: string
              logprobs:
                type: object
              finish_reason:
                type: string
              reasoning_content:
                type: string
        usage:
          $ref: '#/components/schemas/UsageStats'
        x_pioneer:
          $ref: '#/components/schemas/PioneerExtension'
    ChatCompletionRequest:
      type: object
      required:
      - model
      - messages
      properties:
        model:
          type: string
          description: Model ID, project name, or `pioneer/auto` for automatic routing.
        messages:
          type: array
          minItems: 1
          items:
            type: object
            properties:
              role:
                type: string
              content:
                oneOf:
                - type: string
                - type: array
                  items:
                    type: object
              tool_calls:
                type: array
              tool_call_id:
                type: string
        temperature:
          type: number
        max_tokens:
          type: integer
          minimum: 1
          maximum: 131072
        stream:
          type: boolean
          default: false
        stop:
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        response_format:
          type: object
        tools:
          type: array
        tool_choice:
          oneOf:
          - type: string
          - type: object
        top_p:
          type: number
        store:
          type: boolean
          default: true
          description: Persist to inference history. Set false to opt out.
        metadata:
          type: object
          description: Pioneer reads `metadata.project_id` for attribution.
        reasoning:
          type: object
          description: 'Opt-in reasoning controls (OpenRouter-normalized). Keys: enabled, effort (minimal/low/medium/high/xhigh/none), max_tokens, exclude, mode (manual/adaptive, Anthropic-only), display (summarized/omitted, Anthropic-only). effort and max_tokens are mutually exclusive.'
        schema:
          oneOf:
          - type: object
          - type: array
            items:
              type: string
          description: 'Pioneer encoder extension: extraction schema dict.'
        seed:
          type: integer
        n:
          type: integer
        presence_penalty:
          type: number
        frequency_penalty:
          type: number
        user:
          type: string
    PioneerExtension:
      type: object
      description: Pioneer-specific extension on OpenAI-compatible responses.
      properties:
        inference_id:
          type: string
          description: Pioneer inference record ID. Use with GET /inferences/{inference_id} to poll for async LLM-judge results. Null when persistence was disabled.
        routed_model:
          type: string
          description: Actual backend model selected by a router project (e.g. `pioneer/auto`). Null when not routed.
    ErrorResponse:
      type: object
      properties:
        detail:
          oneOf:
          - type: string
          - type: object
          description: Human-readable error message or structured detail object.
    TextCompletionStreamChunk:
      type: object
      description: One SSE event payload for /v1/completions when `stream=true`.
      properties:
        id:
          type: string
        object:
          type: string
          enum:
          - text_completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              text:
                type: string
              finish_reason:
                type: string
              reasoning_content:
                type: string
        usage:
          $ref: '#/components/schemas/UsageStats'
        x_pioneer:
          $ref: '#/components/schemas/PioneerExtension'
    ChatCompletionResponse:
      type: object
      required:
      - id
      - object
      - created
      - model
      - choices
      - usage
      properties:
        id:
          type: string
        object:
          type: string
          enum:
          - chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                type: object
              finish_reason:
                type: string
        usage:
          $ref: '#/components/schemas/UsageStats'
        x_pioneer:
          $ref: '#/components/schemas/PioneerExtension'
    ChatCompletionStreamChunk:
      type: object
      description: 'One SSE event payload when `stream=true`. Terminal chunk carries `finish_reason` and optionally `usage` and `x_pioneer`. Stream ends with `data: [DONE]`.'
      properties:
        id:
          type: string
        object:
          type: string
          enum:
          - chat.completion.chunk
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              delta:
                type: object
                properties:
                  content:
                    type: string
                  reasoning_content:
                    type: string
                    description: Chain-of-thought tokens (de facto vLLM/DeepSeek/Fireworks/OpenRouter extension).
                  tool_calls:
                    type: array
              finish_reason:
                type: string
        usage:
          $ref: '#/components/schemas/UsageStats'
        x_pioneer:
          $ref: '#/components/schemas/PioneerExtension'
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: Pioneer API key. Generate one at https://agent.pioneer.ai/settings/api-keys. Keys begin with `pio_sk_`.
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Supabase access token or Pioneer API key as a Bearer token.
Fastino Labs openai-compat API

Documentation

Specifications

Other Resources

OpenAPI Specification
