OpenAI-compatible embeddings proxy. A 200 response contains one embedding per input; partial or truncated internal encode success is treated as a 500 INTERNAL_ERROR instead of returning a partial 200. Every error path returns the OpenAI {error:{message,type,param,code}} envelope (inner SIE-native encode failures are translated), so an openai-client error handler works unchanged.
Request
- The document declares no server URL.
- Auth
- HTTP bearer
- or API key in header x-api-key
Headers
Preferred GPU or machine profile
Explicit pool routing override
Client SDK version for skew warnings
Require local serving through a current worker execution fence. A selected remote profile returns 400; no verified local worker returns retryable 503. Duplicate or other values return 400.
Request body
Response
OpenAI-compatible embeddings response
Changes
- 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 - info
added the optional property
/////to the response with the status
- info
- info
added the new optional
headerrequest parameterX-SIE-Remote
- info