Proxy to OpenAI-Compatible Chat Completions
Changed onProxy requests to OpenAI-compatible chat completions APIs and return the full response payload. Supports multiple providers via model parameter format: "model_name" (defaults to OpenAI), "provider/model_name", or "provider:model_name". Works with providers that offer OpenAI-compatible endpoints.
Request
- Base URLhttp://localhost:8000
- URLhttp://localhost:8000/api/llm/openai/chat/completions
- AuthAPI key in header Authorization
Request body
Response
Chat completion response
Changes
- breaking
the response's body type changed from no type to
objectfor status - breaking
the response's body type changed from no type to
objectfor status - info
added the optional property
to the response with the status - info
added the optional property
to the response with the status - info
added the optional property
to the response with the status - info
added the optional property
to the response with the status - info
added the optional property
to the response with the status - info
added the optional property
to the response with the status - info
added the optional property
to the response with the status
- breaking
- breaking
request body became required
- breaking
added to the
//request propertyallOflist - breaking
removed the enum value
assistantof the request property// - breaking
removed the enum value
systemof the request property// - breaking
removed the enum value
userof the request property// - breaking
the
request property's minLength was increased from0to1 - breaking
the
//request property type changed fromstringto no type - breaking
the
//request property type changed fromstringto no type - info
added the new optional request property
// - info
added the new optional request property
// - info
added the media type
application/x-www-form-urlencodedto the request body - info
added the media type
multipart/form-datato the request body - info
the request property
//became nullable - info
the request property
//became optional
- breaking