fix(openai): subtract cached tokens from input tokens to avoid double counting#176
Merged
andreynering merged 1 commit intomainfrom Mar 18, 2026
Merged
fix(openai): subtract cached tokens from input tokens to avoid double counting#176andreynering merged 1 commit intomainfrom
andreynering merged 1 commit intomainfrom
Conversation
… counting OpenAI's API reports prompt_tokens/input_tokens INCLUDING cached tokens, while also separately reporting cached_tokens in prompt_tokens_details. This caused double-counting when users summed InputTokens + CacheReadTokens. For example, if OpenAI reports: - prompt_tokens: 1000 (includes 900 cached) - cached_tokens: 900 Before this fix, fantasy reported: - InputTokens: 1000 - CacheReadTokens: 900 After this fix, fantasy reports: - InputTokens: 100 (non-cached only) - CacheReadTokens: 900 This matches the behavior of Vercel AI SDK and prevents billing miscalculations when pricing input tokens and cache read tokens separately. See: https://platform.openai.com/docs/guides/prompt-caching#requirements 💘 Generated with Crush Assisted-by: Kimi K2.5 via Crush <crush@charm.land>
kylecarbs
approved these changes
Mar 18, 2026
aymanbagabas
approved these changes
Mar 18, 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
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
OpenAI's API reports prompt_tokens/input_tokens INCLUDING cached tokens, while also separately reporting cached_tokens in prompt_tokens_details. This caused double-counting when users summed InputTokens + CacheReadTokens.
For example, if OpenAI reports:
Before this fix, fantasy reported:
After this fix, fantasy reports:
This matches the behavior of Vercel AI SDK and prevents billing miscalculations when pricing input tokens and cache read tokens separately.
See: https://platform.openai.com/docs/guides/prompt-caching#requirements
💘 Generated with Crush
Assisted-by: Kimi K2.5 via Crush crush@charm.land