This release adds 3 notable features for engineering teams evaluating rollout.
Published 1mo
Model Serving & MLOps
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
anthropic
cost-optimization
devtools
github-action
llm
mlops
+3 more
openai
python
static-analysis
Summary
AI summaryStatic analysis tool for estimating LLM API call costs in Python code
Full changelog
tokentoll v0.1.0
Catch LLM cost changes in code review. Infracost for LLM spend.
Features
- Static analysis of Python code for LLM API calls using the
astmodule - 5 SDK detectors: OpenAI, Anthropic, Google GenAI, LiteLLM, LangChain
- Cost estimation using real pricing data (2200+ models from LiteLLM)
- Diff engine showing cost impact of changes between git refs
- 3 output formats: CLI table, Markdown (for PR comments), JSON
- GitHub Action with automatic PR comments via sticky comment
- Zero runtime dependencies -- stdlib only
- Smart pricing cache with auto-refresh and bundled fallback
Install
pip install tokentoll
Quick start
tokentoll scan . # Find all LLM calls and their costs
tokentoll diff HEAD~1 # Show cost impact of your last commit
GitHub Action
- uses: Jwrede/[email protected]
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Tokentoll
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]