LiteLLM 1.110.0 released
A major release with numerous fixes across providers, improved error handling, and new features for model management and authentication.
What changed in 1.110.0
- Fixed chat audio format handling for Gemini, Anthropic beta headers alignment, and Bedrock token counting for Claude models
- Improved streaming and fallback behavior for encrypted reasoning, Azure native streaming, and provider field preservation
- Added support for latest OpenAI audio models, Wally as OpenAI-compatible provider, and Parallel AI web-grounded decisions
- Enhanced model catalog with successor_model, deprecation_source, and fedramp_uplift_multiplier capabilities
- Fixed cost tracking for web search, video processing, and improved budget window charging when cached credentials expire
Check before you update
- Gemini unsupported chat audio formats now return 400 and are dropped
- Anthropic beta header allowlist synced with Anthropic, Vertex AI, and Azure AI accepted headers
- Bedrock Claude models now use their own default max_tokens instead of inherited values
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 is the latest stable release we track. |
| Release pace | 43 stable releases in the last 30 days; 1.110.0 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 Nov 5, 2026) |
| Downloads, last 7 days | 24.1M up 6.1% |
| Gid Score | 76 #1 in Agent tooling for cost, context and memory |