LiteLLM 1.106.0 released
A major release with Docker image signature verification, MCP server changes, and numerous fixes across tracing, proxy, and UI components.
What changed in 1.106.0
- Stdio MCP servers are now disabled by default; enable explicitly if needed.
- Docker images are now signed with cosign for verification; quickstart commands added for gateway, Postgres, and admin UI setup.
- Fixed tracing configuration, spend log handling, and Postgres connection issues in the proxy.
- Added support for new providers including Laya gateway, Bespoke Nimble, and Scaleway rerank; improved model pricing and deprecation dates.
- UI improvements include Tencent provider registration, Lens dashboard reorganization, and better trace inspection tools.
Check before you update
- Stdio MCP servers disabled by default; must be explicitly enabled to use.
Summarised by AgentGid from BerriAI's official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
LiteLLM at a glance
| What it is | An AI gateway and Python SDK that calls 100+ model APIs through one OpenAI-style interface, with spend tracking, budgets, rate limits, fallbacks, guardrails and logging. |
|---|---|
| Latest version | 1.104.5, Oct 21, 2026. This page is about an earlier release. |
| Release pace | 36 stable releases in the last 30 days; 1.106.0 came 1 day after the previous one |
| Price | Free (OSS). The SDK and proxy are open source and free. An enterprise edition with SSO, audit logs and support is sold separately. Official pricing ↗ (checked Oct 9, 2026) |
| Downloads, last 7 days | 22.9M up 4.3% |
| Gid Score | 72 #2 in Agent tooling for cost, context and memory |
