LLM

Proxy OpenAI-compatible legacy completion

Credit-gated legacy completions endpoint. Request and response shape follows OpenAI-compatible /completions semantics.

post/v1/llm/completions

Request

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

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.

max_tokensinteger

Maximum output tokens to reserve and request.

modelstring required

Desktop-facing LLM model id.

promptstring required

Prompt string or prompt array forwarded to the upstream.

streamboolean

When true, stream upstream completion events.

temperaturenumber

Sampling temperature forwarded to the upstream.

{
  "max_tokens": 512,
  "model": "openai/gpt-4.1-mini",
  "prompt": "Summarize this account.",
  "temperature": 0.2
}

OpenAI-compatible JSON response, or text/event-stream when stream=true.

LLMGatewayResponse required

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

No operation changes recorded.