LLM

Proxy OpenAI-compatible embeddings

Credit-gated embeddings endpoint. The gateway requires a model, reserves credits, forwards the request, and records usage.

post/v1/llm/embeddings

Request

Base URL: / (relative, and the document was published on a file host, not at the API’s origin)
URL: /v1/llm/embeddings
Auth: HTTP bearer

Headers

Idempotency-Keystring required

Required stable key for metered POST retries. Reusing the same key for the same user, route, and method reuses the same credit reservation anchor.

x-solomon-use-casestring

Optional feature/use-case label recorded in LLMUsage for cost allocation.

x-solomon-sub-use-casestring

Optional sub-use-case label recorded in LLMUsage.

x-solomon-agent-namestring

Optional agent name recorded in LLMUsage.

Request body

dimensionsinteger

Optional embedding dimensions for models that support it.

encoding_formatstring nullable

Embedding encoding format forwarded to the upstream.

inputunknown required

modelstring required

Desktop-facing embedding model id.

Example request

{
  "dimensions": 1536,
  "encoding_format": "float",
  "input": [
    "customer invoice",
    "payment risk"
  ],
  "model": "openai/text-embedding-3-small"
}

Response

OpenAI-compatible upstream response.

LLMGatewayResponse required

OpenAI-compatible upstream response. For streaming calls, the same endpoint returns text/event-stream chunks.

Changes

No operation changes recorded.