Fastino Labs Openai Compat API
OpenAI-compatible endpoints. Use with the OpenAI SDK by setting base_url=https://api.pioneer.ai/v1.
OpenAI-compatible endpoints. Use with the OpenAI SDK by setting base_url=https://api.pioneer.ai/v1.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/fastino-labs:fastino-labs-openai-compat-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Pioneer Inference 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:
schemas:
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'
ErrorResponse:
type: object
properties:
detail:
oneOf:
- type: string
- type: object
description: Human-readable error message or structured detail object.
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'
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).
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
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
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
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'
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.
responses:
PaymentRequired:
description: Insufficient credits or no active billing plan.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
ModelNotFound:
description: Model ID not found or not yet deployed.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
ValidationError:
description: Request body failed schema validation.
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationErrorResponse'
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'
Unauthorized:
description: Missing or invalid API key.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
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.