v1.88.5 - Vertex Batch Uploads & Stream Cost Recovery
Deploy this version​
- Docker
- Pip
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
docker.litellm.ai/berriai/litellm:1.88.5
pip install litellm==1.88.5
v1.88.5 is a patch release on top of v1.88.4. It streams OpenAI→Vertex batch JSONL uploads instead of buffering them in memory, backports cost-tracking recovery for interrupted Anthropic streams, adds a no-mcp-servers sentinel that scopes a key to zero MCP servers, and bumps OpenSSL plus runtime dependencies (cryptography, aiohttp) for CVE coverage. The bundled litellm-enterprise package is bumped to 0.1.42.post1.
What's Changed​
- fix(passthrough): recover output tokens for interrupted anthropic streams - PR #30787
- fix(proxy): record partial spend on the failure row for interrupted streams - PR #30788
- feat(mcp): scope a key to zero MCP servers with no-mcp-servers sentinel - PR #31029
- fix(passthrough,streaming): recover cost on interrupted and agentic Anthropic streams - PR #31035
- fix(vertex/files): stream OpenAI->Vertex batch JSONL uploads - PR #31036
- fix(docker): bump wolfi-base digest to patch openssl CVE-2026-34182 - PR #31133
Full Changelog​
https://github.com/BerriAI/litellm/compare/v1.88.4...v1.88.5