LiteLLM 1.108.5 released
An LTS patch release fixing OpenAI keyless identity authentication, tool call streaming, message API parameters, and transcription cost calculation.
What changed in 1.108.5
- OpenAI keyless workload identity deployments no longer return 401 errors on image edits, audio, files, batches and related routes.
- Ollama parallel tool calls in streams now receive correct indices instead of all being assigned index 0.
- Messages API accepts parameters listed in deployment's additional_drop_params without returning 400 errors.
- Transcription costs for some FLAC files are now calculated correctly.
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; 1.108.5 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 |
