This release adds 5 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+7 more
Summary
AI summaryAdded llm-router budget CLI, Dashboard Budget tab, Helicone and LiteLLM spend integrations, and multi-source aggregation.
Full changelog
What's new
llm-router budgetCLI —list,set <provider> <amount>,remove <provider>with persistent storage in~/.llm-router/budgets.json- Dashboard Budget tab — editable per-provider cap inputs, live Save, Prometheus
/metricsendpoint - Helicone integration — routing property headers on every call + optional spend pull (
LLM_ROUTER_HELICONE_PULL=true) - LiteLLM BudgetManager integration — read per-provider monthly spend from LiteLLM Proxy SQLite DB
- Multi-source spend aggregation — local SQLite + Helicone + LiteLLM spend used concurrently; max ensures pressure is never under-reported
- Onboarding nudges — setup wizard and
llm_budgettool prompt uncapped providers - 35 new tests (828 total)
Upgrade
pip install --upgrade claude-code-llm-router && llm-router install
Quick start with budget caps
llm-router budget set openai 20
llm-router budget set gemini 5
llm-router budget list
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]