openai.internal.chat_invoke

The one internal entry point: render, send, normalize — one model turn.

Reference version

Signature

function openai.internal.chat_invoke(
input: ai.ModelTurnInput,
capture_wire: bool = …,
request_timeout_ms: int | null = …
) -> ai.ModelTurn throws baml.errors.InvalidArgument | baml.errors.Io | baml.errors.Timeout | baml.json.SerializationError | ai.errors.Failure

The one internal entry point: render, send, normalize — one model turn.

Source:<builtin>/openai/ns_internal/chat.bamlbytes 5470055207