docs(pass_through): correct cost tracking coverage claims - #894
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Author
|
bugbot run |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
✅ Bugbot reviewed your changes and found no new issues!
Comment @cursor review or bugbot run to trigger another review on this PR
Reviewed by Cursor Bugbot for commit 4d5c1cb. Configure here.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The passthrough docs' cost tracking claims drifted from the code. openai_passthrough.md said cost tracking is not supported, but the proxy tracks chat completions, image generations, image edits, and the Responses API there today, with embeddings landing in BerriAI/litellm#36660. azure_passthrough.md had the same stale flat no while v1 API paths are tracked through the shared OpenAI handler, and intro.md claimed usage is tracked across all endpoints, which overstates it. mistral.md and vllm.md were checked too and stay as they are: no cost handler exists for either, so their tables are still accurate
This updates the three stale files, points base_url at /openai_passthrough consistently in the OpenAI client example, and adds an embeddings curl example. Verified live against a DB-backed proxy running the BerriAI/litellm#36660 branch: a /openai_passthrough/v1/embeddings call for text-embedding-3-small wrote a spend log row and billed the key exactly (6 tokens, $0.00000012), and on today's base branch the same call bills nothing. Best merged after BerriAI/litellm#36660 so the embeddings claim is never ahead of the code
Note
Cursor Bugbot is generating a summary for commit 4d5c1cb. Configure here.