LiteLLM 1.108.4 released
An LTS patch release fixing issues across Bedrock, Vertex AI, Messages API, and the SDK.
What changed in 1.108.4
- Fixed Bedrock failures with Claude's signed thinking in conversations for GLM, GPT-6 Luna and Nova 2 models.
- Fixed Vertex AI Claude batches failing at creation and Messages API dropping encrypted reasoning between turns.
- Fixed video polling failures with per-model keys and team keys using wrong BYOK deployments.
- Fixed SDK methods failing with missing mcp module on base installs.
- Bedrock guardrail enforcement now prioritizes model configuration over caller-provided guardrails.
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; 1.108.4 came 2 days 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 | 23.8M up 5.3% |
| Gid Score | 76 #1 in Agent tooling for cost, context and memory |
