fix(openai): add "fast" to the responses ServiceTier literal - #7044
Open
philipp-eisen wants to merge 1 commit into
Open
fix(openai): add "fast" to the responses ServiceTier literal#7044philipp-eisen wants to merge 1 commit into
philipp-eisen wants to merge 1 commit into
Conversation
OpenAI renamed "Priority processing" to "Fast mode" on 2026-07-30; "fast" and "priority" are now aliases for the same tier. This matches the openai SDK's own service_tier literal and lets callers pass service_tier="fast" without a cast. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
OpenAI renamed "Priority processing" to "Fast mode" on 2026-07-30 and changed the accepted
service_tiervalues (docs, FAQ).fastandpriorityare aliases for the same tier: a request withservice_tier="fast"succeeds, and the response still reportsservice_tier="priority".The
ServiceTierliteral in the responses LLM predates the rename, so passingservice_tier="fast"needs acasttoday. This PR adds"fast"to the literal, in the same member order as the openai SDK's own type (checked on openai 2.53.0:Literal["auto", "default", "flex", "scale", "priority", "fast"]).Note that the API no longer accepts
"scale". Requesting it on chat completions fails (verified against the live API on 2026-08-30):So the API currently accepts
auto,default,fast,flex,priority. I kept"scale"in the literal so existing type-checked callers don't break; whether to deprecate or remove it is up to you.For awareness, two related spots left untouched: the chat-completions path types
service_tieras plainstr, andlivekit-agents/livekit/agents/inference/llm.pyhas the same pre-rename literal for the LiveKit inference gateway, which defines its own accepted set.