This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+7 more
Affected surfaces
Summary
AI summaryAdded yearly savings projection and Monday weekly digest in session summaries.
Full changelog
What's new
- Yearly savings projection in session-end summary —
📈 Projection: ~$X/year · ~Xk tok/yearextrapolated from 7-day average - Monday weekly digest in session-start — shows last 7 days: calls, tokens, USD saved, yearly projection. Fires once/week
- Shadow / suggest / enforce activation modes — control routing enforcement via
LLM_ROUTER_ENFORCEor.llm-router.yml:shadow→ passive observation, no blockingsuggest→ soft hint, logs violations onlyenforce→ blocks non-routed tool calls (default)
llm-router onboardwizard — detects Ollama/Codex/API keys, recommends profile, writes.env, runs install
Upgrade
```bash
pip install --upgrade claude-code-llm-router
llm-router install
```
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 ypollak2/llm-router
Subscription-aware LLM router for Claude Code. Routes tasks to 20+ providers (OpenAI, Gemini, Groq, Ollama, Codex) based on complexity classification, Claude subscription pressure, and cost. Free tasks stay on Claude subscription; expensive tasks fall back to the cheapest capable model. Includes 30 MCP tools, 6 auto-routing hooks, semantic dedup cache, prompt caching, daily spend cap, and a live web dashboard.
Related context
Related tools
Beta — feedback welcome: [email protected]