{{ message }}
Repository navigation
fix: move Fireworks AI calls off decommissioned serverless models (deadline passed September 25) - #8923
Open
23821 wants to merge 1 commit into
Conversation
…adline passed September 25)
Contributor
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
| const FIREWORKS_WIRE_NAMES: Record<string, string> = { | ||
| 'glm-5.3': 'accounts/fireworks/models/glm-5p3', | ||
| 'glm-5.2': 'accounts/fireworks/models/glm-5p2', | ||
| 'glm-5.2': 'accounts/fireworks/models/glm-5p3', |
Contributor
There was a problem hiding this comment.
glm-5.2 now runs the same model as glm-5.3, but keeps the old cached-input price. models.ts lists cachedInput: 0.14 for fireworks/glm-5.2 and 0.26 for fireworks/glm-5.3.
If Fireworks reports cached tokens, conversation records and traces still price them using request.model. Requests using fireworks/glm-5.2 therefore record a lower cost for the same served model. Keep the alias if desired, but update its price to match the replacement.
|
The latest updates on your projects. Learn more about Vercel for GitHub. 1 Skipped Deployment |
This branch was previously deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fireworks AI decommissioned the serverless model glm-5p2 on September 25, 2026, and calls for
glm-5.2still went to it. This pointsglm-5.2at the replacement wire idaccounts/fireworks/models/glm-5p3inapps/sim/providers/fireworks/utils.ts, and updates the expected ids inutils.test.tsandindex.test.ts. Fireworks changelog: https://docs.fireworks.ai/updates/changelogProduct update (if relevant)
Users of
fireworks/glm-5.2now get glm-5p3, which may sound or behave differently. Team decision still open: keep thefireworks/glm-5.2catalog id aliasing glm-5p3, or retire it in favor offireworks/glm-5.3, which already maps to glm-5p3.Type of Change
Testing
Tests could not be run. Dependency install failed with
npm error EUNSUPPORTEDPROTOCOL(Unsupported URL Type "workspace:": workspace:*), so the change is unverified. Reviewers should check that the two updated test files still test the right thing, and that theglm-5.2mapping is what the team wants.Checklist
Screenshots/Videos
Not applicable: no UI change.
Prepared with YakBarber, a tool I'm building that updates code when an API changes (the check is open source), and reviewed by me before sending. It was sent once, to this repository only; if it isn't useful, feel free to close it.