LiteLLM 1.108.7 released
An LTS patch release fixing billing, streaming sequences, and provider compatibility issues across multiple services.
What changed in 1.108.7
- Azure AI Foundry now supports image edits on custom-named deployments; AWS Bedrock supports image search on knowledge bases.
- Fixed incorrect billing rates for Gemini image calls, thinking tokens, and Vertex Priority tokens.
- Fixed Responses API streaming events with missing or repeated sequence numbers and tool call handling in MCP follow-ups.
- Fixed Baseten model listing and reasoning_effort parameter handling; fixed Bedrock failures in response chains.
- Added Gemini batches support with output download and spend tracking.
Check before you update
- Set drop_params: true when sending Responses-only fields like max_tool_calls to bridged providers, or stop sending those fields; otherwise requests return 400.
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 | 1.106.10, Nov 14, 2026. This page is about an earlier release. |
| Release pace | 41 stable releases in the last 30 days; 1.108.7 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 | 23.8M up 5.3% |
| Gid Score | 76 #1 in Agent tooling for cost, context and memory |
