base_url to https://api.pioneer.ai/v1, authenticate with your Pioneer API key, and pass your training job ID as the model. Pioneer-specific fields like schema can be passed via extra_body in the Python SDK or included directly in the JSON body.
Endpoints
Configure the OpenAI SDK
Point the SDK at Pioneer’s base URL and supply your Pioneer API key:Chat completions
POST /v1/chat/completions accepts the same request shape as the OpenAI Chat Completions API. Pass your training job ID as model and include Pioneer-specific fields like schema in the request body or via extra_body.
Text completions
POST /v1/completions supports the legacy completions format with a prompt field.
List available models
UseGET /v1/models to retrieve the list of models you can use with these endpoints.
Streaming
All completions endpoints support streaming. Setstream=True in the SDK or "stream": true in the request body.
Passing Pioneer-specific fields
Theschema field is a Pioneer extension. In the OpenAI Python SDK, pass it via extra_body so it is included in the request without affecting SDK validation. In a raw HTTP request, include it at the top level of the JSON body alongside standard fields like model and messages.
Related
- Pioneer native inference — direct Pioneer endpoint with full schema documentation
- Anthropic-compatible inference — use the Anthropic SDK instead
- Inference history and feedback — retrieve past results and submit corrections