LiteLLM 1.108.11 released
An LTS patch release fixing issues across multiple providers, APIs, and deployment scenarios.
What changed in 1.108.11
- Azure, AWS Bedrock, Vertex AI and Gemini now handle edge cases in reasoning parameters and message processing correctly.
- OpenRouter, Cohere, and other providers fixed to stop sending malformed requests and always use configured API endpoints.
- Chat completions, responses, and messages APIs no longer send internal parameters to providers or drop content in streams.
- SSO login flow, embeddings handlers, and proxy memory management corrected to work as expected.
- Added native support for custom providers using generateContent.
Check before you update
- Team admins can no longer set os.environ/ values in model writes; only proxy admins retain this capability.
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. The same gateway also serves A2A agents and MCP t… |
|---|---|
| Latest version | 1.110.0, Nov 18, 2026. This page is about an earlier release. |
| Release pace | 43 stable releases in the last 30 days; 1.108.11 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 Nov 5, 2026) |
| Downloads, last 7 days | 24.1M up 6.1% |
| Gid Score | 76 #1 in Agent tooling for cost, context and memory |