"Fix: Subtract cached tokens from batch cost calculation"

[priyam-that]

• Fixes issue Cost calculation incorrectly charges for cached tokens #19680 where cached tokens were being charged in batch operations
• Handles both cache_read_input_tokens (Anthropic/OpenAI) and prompt_tokens_details.cached_tokens (z.ai/Bedrock/Gemini) formats
• Applies fix to both input_cost_per_token_batches and input_cost_per_token paths
• Prevents overcharging users by 10x+ on requests with high cache hit rates"

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

CI (LiteLLM team)

CI status guideline:

• 50-55 passing tests: main is stable with minor issues.
• 45-49 passing tests: acceptable but needs attention
• <= 40 passing tests: unstable; be careful with your merges and assess the risk.

• Branch creation CI run
  Link:

• CI run for the last commit
  Link:

• Merge / cherry-pick CI run
  Links:

Type

🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test

Changes

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
litellm	Ready	Preview, Comment	Jan 24, 2026 6:08pm

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}