feat: expose serviceTier in CompletionUsage from OpenAI Responses API#1205
Merged
toubatbrian merged 2 commits intolivekit:mainfrom Apr 9, 2026
Merged
Conversation
🦋 Changeset detectedLatest commit: bcfa8c2 The changes in this PR will be included in the next version bump. This PR includes changesets to release 22 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
8015d32 to
4a1f9d5
Compare
OpenAI returns service_tier (e.g. "default", "priority", "flex") in every API response. This adds it to CompletionUsage and reads it in the Responses plugin's handleResponseCompleted. Changes: - Add serviceTier?: string to CompletionUsage interface - Read event.response.service_tier in Responses LLM
4a1f9d5 to
91725a5
Compare
toubatbrian
reviewed
Apr 9, 2026
Contributor
toubatbrian
left a comment
There was a problem hiding this comment.
LG! Can you fix the build error in CI. thanks
Declare service_tier on wsResponseCompletedEventSchema so the WS Responses handler can read it without a double cast, mirroring the pattern in responses/llm.ts. Fixes prettier line-length lint error.
Contributor
Author
|
toubatbrian
approved these changes
Apr 9, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Mirrors livekit/agents#5341 for the JavaScript/TypeScript SDK.
OpenAI returns
service_tierin every API response, indicating the processing tier actually used (e.g."default","priority","flex"). This is important for accurate cost tracking since priority tier has different billing rates.Changes
agents/src/llm/llm.ts: AddserviceTier?: stringtoCompletionUsageinterfaceplugins/openai/src/responses/llm.ts: Readevent.response.service_tierinhandleResponseCompletedand pass it toCompletionUsageBackward Compatible
serviceTieris optional — no impact on existing code