When To Use This
Usetm infer completions when you want the text-completions endpoint instead of chat completions.
Provide the request body as JSON and either include model in the body or pass --model to override it.
Usage
Examples
Send a serverless text-completions request.
Stream text-completion tokens over SSE and fail a stalled stream after 30 seconds of upstream silence.
Options
Inherited Global Options
Auth Scope
- inference-api-key
Caveats
--modeloverrides themodelfield inside the JSON request body.--streamcurrently supports only--output text.

