LiteLLM 1.108.9 released
A patch release backporting fixes and features for response handling, cloud provider integrations, and decision models.
What changed in 1.108.9
- Fixed mixed reasoning and answer preservation in responses, and cache control breakpoints in the chat-to-Responses bridge.
- Bedrock now supports S3 media sources in Converse and OpenAI vector store search filter mapping.
- Azure AI sends reasoning_effort to Foundry Kimi K3 and preserves its reasoning_content; Azure also supports Foundry project and resource /openai/v1 Responses bases.
- Vertex AI includes caller identity labels on requests; Vercel AI Gateway decision models are now available.
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; 1.108.9 came the same day as 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 |