LiteLLM is moving to Rust Read the latest updates.
LiteLLM v1.108.10 (LTS) fixes Vertex Claude 4096-token cap and EU o3 spend
tip
v1.108.10 is a patch release on the 1.108 LTS line. The lts image tag always points to the latest LTS release, so pull docker.litellm.ai/berriai/litellm:lts to stay on the newest LTS patch. See the LTS pilot.
Deploy this version​
- Docker
- Pip
docker run \
-e LITELLM_MASTER_KEY=sk-<paste-a-long-random-key> \
-e DATABASE_URL=postgresql://<user>:<password>@<host>:5432/<dbname> \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
docker.litellm.ai/berriai/litellm:1.108.10
pip install litellm==1.108.10
This release is published as ghcr.io/berriai/litellm:v1.108.10. See the GitHub release and the full releases page.
v1.108.10 is a patch release on top of v1.108.9. There are no new database migrations. The v1.108.10 tag points at 5d6a139.
What's Changed​
- Vertex AI and Gemini: Fixed versioned
claude-*@<version>models stopping at 4096 tokens whenmax_tokensis unset - PR #51863 - Chat completions: Fixed 400 on async Codestral chat with a
filepart and streamed PDF URLs stalling the proxy worker - PR #51860 - Cost tracking and pricing: Fixed $0 spend on deployments whose
base_modelisazure/eu/o3,o4-mini,o1oro3-mini- PR #47497
The cost fix from PR #47497 is backported in PR #51412.
Full Changelog​
https://github.com/BerriAI/litellm/compare/v1.108.9...v1.108.10