Deploy this versionβ
- Docker
- Pip
docker run
-e STORE_MODEL_IN_DB=True
-p 4000:4000
ghcr.io/berriai/litellm:main-v1.71.1-stable
pip install litellm==1.71.1
Key Highlightsβ
LiteLLM v1.71.1-stable is live now. Here are the key highlights of this release:
Performance Improvementsβ
This release includes significant performance enhancements:
- aiohttp Transport: 97% lower median latency (available as feature flag)
File Permissionsβ
v1.71.2-stable brings support for File Permissions and Finetuning APIs to LiteLLM Managed Files. This is great for:
- Proxy Admins: as users can only view/edit/delete files theyβve created - even when using shared OpenAI/Azure/Vertex deployments.
- Developers: get a standard interface to use Files across Chat/Finetuning/Batch APIs.
New Models / Updated Modelsβ
- Gemini VertexAI, Google AI Studio
- Anthropic
- Claude-4 model family support - PR
- Bedrock
- VertexAI
- xAI
xai/grok-3
pricing information - PR
- LM Studio
- Structured JSON schema outputs support - PR
- SambaNova
- Updated models and parameters - PR
- Databricks
- Azure
- Mistral
- devstral-small-2505 model pricing and context window - PR
- Ollama
- Wildcard model support - PR
- CustomLLM
- Embeddings support added - PR
- Featherless AI
- Access to 4200+ models - PR
LLM API Endpointsβ
- Image Edits
- Responses API
- MCP support for Responses API - PR
- Files API
Management Endpoints / UIβ
- Teams
- Keys
- Logs
- Guardrails
- Config.yaml guardrails display - PR
- Organizations/Users
- Audit Logs
/list
and/info
endpoints for Audit Logs - PR
Logging / Alerting Integrationsβ
- Prometheus
- Track
route
on proxy_* metrics - PR
- Track
- Langfuse
- DeepEval/ConfidentAI
- Logging enabled for proxy and SDK - PR
- Logfire
- Fix otel proxy server initialization when using Logfire - PR
Authentication & Securityβ
- JWT Authentication
- Custom Auth
- Support for switching between custom auth and API key auth - PR
Performance / Reliability Improvementsβ
- aiohttp Transport
- Background Health Checks
- Improved reliability - PR
- Response Handling
- Thread Management
- Removed error-creating threads for reliability - PR
General Proxy Improvementsβ
Bug Fixesβ
This release includes numerous bug fixes to improve stability and reliability:
LLM Provider Fixes
Authentication & Users
Database & Infrastructure
UI & Display
Model & Routing
New Contributorsβ
- @DarinVerheijke made their first contribution in PR #10596
- @estsauver made their first contribution in PR #10929
- @mohittalele made their first contribution in PR #10665
- @pselden made their first contribution in PR #10899
- @unrealandychan made their first contribution in PR #10842
- @dastaiger made their first contribution in PR #10946
- @slytechnical made their first contribution in PR #10881
- @daarko10 made their first contribution in PR #11006
- @sorenmat made their first contribution in PR #10658
- @matthid made their first contribution in PR #10982
- @jgowdy-godaddy made their first contribution in PR #11032
- @bepotp made their first contribution in PR #11008
- @jmorenoc-o made their first contribution in PR #11031
- @martin-liu made their first contribution in PR #11076
- @gunjan-solanki made their first contribution in PR #11064
- @tokoko made their first contribution in PR #10980
- @spike-spiegel-21 made their first contribution in PR #10649
- @kreatoo made their first contribution in PR #10927
- @baejooc made their first contribution in PR #10887
- @keykbd made their first contribution in PR #11114
- @dalssoft made their first contribution in PR #11088
- @jtong99 made their first contribution in PR #10853
Demo Instanceβ
Here's a Demo Instance to test changes:
- Instance: https://demo.litellm.ai/
- Login Credentials:
- Username: admin
- Password: sk-1234