feat: enhance LiteLLM metadata extraction by adding cost retrieval from response headers #567
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Outdated suggestions cannot be applied.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.
Pull Request
Summary
Adds a fallback mechanism to capture cost from LiteLLM response headers when
response_costis zero or unavailable.Changes
extract_litellm_metadatato track response headers and check for cost fallback_extract_cost_from_headershelper function to parsex-litellm-response-costandx-litellm-response-cost-originalheadersContext
In some cases, the
response_costfrom LiteLLM's hidden params is returned as0, but the actual cost is available in the response headers underx-litellm-response-cost. This fix ensures we capture cost data from headers as a fallback when the primary source fails.Applies to both streaming and non-streaming completions.
Testing