Repository navigation
fix(google-ai): bill Gemini cached prompt tokens separately - #1496
Open
pcbeingused333 wants to merge 1 commit into
Open
pcbeingused333 wants to merge 1 commit into
pcbeingused333 wants to merge 1 commit into
Conversation
Gemini's PromptTokenCount includes tokens served from the context cache. They were reported entirely as fresh input and CachedTextInputTokens was never set, so cached tokens were charged at the full input price.
Contributor
Qodo reviews are paused for this user.Troubleshooting steps vary by plan Learn more → On a Teams plan? Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No linked issue (sibling of #1486: same usage-accounting gap, here for cached input instead of thinking tokens).
Gemini's
UsageMetadata.PromptTokenCountincludes the tokens served from the context cache (CachedContentTokenCount). The Google AI provider reported the whole prompt count asTextInputTokensand never setCachedTextInputTokens, so cached tokens were charged at the full input price inTokenStatistics. The OpenAI, Azure OpenAI, DeepSeek and Anthropic providers already split the two.Fix:
ProviderHelper.GetInputTokens(prompt count minus cached count, floored at 0) andGetCachedInputTokens, used by the three usage sites in the chat provider and the text completion provider.Test:
GoogleAiUsageTestscovers the split, the no-cache case and null usage. They fail on main (the helpers do not exist; the old code reported 1000 fresh input tokens and 0 cached for a 1000/800 usage).This change was prepared with the assistance of an AI coding tool (Claude Code); the author is responsible for the submission.