Reference

Not supported yet

The OpenAI endpoints and parameters this API does not implement, stated plainly, so you find out here rather than at a 404.

Chat completions is the surface. Everything below is absent, and knowing that now is worth more than discovering it at a 404.

Endpoints

EndpointStatus
POST /v1/chat/completionsImplemented
GET /v1/modelsImplemented, public
GET /v1/models/{id}Implemented, public
POST /v1/embeddingsNot implemented
POST /v1/completions (legacy)Not implemented, and not planned. Use chat completions
POST /v1/images/generationsNot implemented
POST /v1/audio/transcriptionsImplemented. srt and vtt output are not
POST /v1/audio/speechImplemented. Streaming synthesis is not
POST /v1/moderationsNot implemented
POST /v1/responsesNot implemented
Assistants, threads, files, batches, fine-tuningNot implemented

Parameters

ParameterStatus
nNot supported. Ask twice
logit_biasNot forwarded
userAccepted and ignored. We already attribute usage to your key
service_tierNot applicable. There is no priority lane, and nothing here will claim one

Anything else in the request body that we do not implement is passed through to the provider rather than rejected, which is what every OpenAI-compatible API does. If a model does not support something you sent, that is a 400 naming the parameter before any billable work. See Errors.

Metering is unit-agnostic, and speech proved it

Every usage record carries a unit rather than assuming tokens. Today that is token for text, second for transcription and character for synthesis.

This was built before there was anything but text to meter, on the argument that hardcoding tokens would force a rewrite of the billing path on the day audio shipped. Audio shipped on 31 July 2026 and the pricing function needed no new arithmetic — the same line prices all three units, because the unit changes what the caller counts, not how the counting is priced.