Skip to content

Tokentoll

v0.5.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

anthropic cost-optimization devtools github-action llm mlops
+3 more
openai python static-analysis

Summary

AI summary

Per‑SDK default models are now configurable via .tokentoll.yml with a default_models dict.

Full changelog

Per-SDK default models

Dynamic LLM calls now resolve to sensible per-SDK defaults instead of always falling back to gpt-4o:

  • OpenAI calls default to gpt-4o
  • Anthropic calls default to claude-sonnet-4-20250514
  • Google GenAI calls default to gemini-2.0-flash
  • LiteLLM calls default to gpt-4o
  • LangChain calls default to gpt-4o

Config: default_models support

The .tokentoll.yml config file now supports a default_models dict for per-SDK overrides at both project and path levels:

default_models:
  openai: gpt-4o-mini
  anthropic: claude-haiku-3-20240307

Resolution order: per-SDK config > generic default_model > built-in SDK defaults.

Full Changelog

https://github.com/Jwrede/tokentoll/compare/v0.4.0...v0.5.0

View diff on GitHub

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

Share on X Share on Bluesky

Track Tokentoll

Get notified when new releases ship.

Sign up free

About Tokentoll

All releases →

Related context

Beta — feedback welcome: [email protected]