v1.71.1-stable

What's Changed

• add docs for spend logs by @jugaldb in #10913
• [QA/Guardrails] Allow editing guardrail entity configs by @ishaan-jaff in #10918
• [UI QA Guardrails] - Minor UI Fixes by @ishaan-jaff in #10920
• [CI/CD] Fix - linting cryptography error by @ishaan-jaff in #10921
• LiteLLM Stable release notes by @krrishdholakia in #10919
• docs apply guardrail endpoint by @ishaan-jaff in #10923
• [Docs] Pii masking with LiteLLM by @ishaan-jaff in #10924
• Add provider Featherless AI (access to 4200+ models) by @DarinVerheijke in #10596
• fix(vertex_llm_base.py): remove quota_project_id parameter from crede… by @krrishdholakia in #10915
• Enable structured JSON schema outputs in LM Studio by @estsauver in #10929
• update sambanova models and parameters by @jhpiedrahitao in #10900
• Fix Cohere Rerank Provider by @keyute in #10822
• add skip server startup flag to cli by @mohittalele in #10665
• Allow passed in vertex_ai credentials to be authorized_user type by @pselden in #10899
• fix: handle DB_USER, DB_PASSWORD, DB_HOST problem I faced, since this… by @unrealandychan in #10842
• Add keys and members count in team info by @NANDINI-star in #10950
• Update github.md by @dastaiger in #10946
• docs: add llms.txt and llms_full.txt for LLM-friendly scraping by @colesmcintosh in #10961
• [Fix] Invitation Email does not include the invitation link by @ishaan-jaff in #10958
• Enable key reassignment on UI + Show 'updated at' column for key in all keys table by @krrishdholakia in #10960
• Update existing model's model info on UI + Show model access groups when creating keys/teams on UI by @krrishdholakia in #10965
• Validate migrating keys to teams + Fix mistral image url on async translation by @krrishdholakia in #10966
• add cla to docs by @jugaldb in #10963
• [Fix] List Guardrails - Show config.yaml guardrails on litellm ui by @ishaan-jaff in #10959
• fix: vertex show clear exception on failed refresh by @ishaan-jaff in #10969
• [Feature] Add supports_computer_use to the model list by @slytechnical in #10881
• [Feat] - Add Support for Showing Passthrough endpoint Error Logs on LiteLLM UI by @ishaan-jaff in #10990
• added support to credential delete to support slashes in the curl by @jugaldb in #10987
• Add new gemini preview models + Fix cohere v2 embedding 'embedding_types' param mapping by @krrishdholakia in #10991
• Litellm add new gemini models by @krrishdholakia in #10998
• [Feat] Prometheus - Track route on proxy_* metrics by @ishaan-jaff in #10992
• fix: default role for JWT authentication by @ishaan-jaff in #10995
• fix(internal_user_endpoints.py): allow resetting spend/max budget on /user/update + Fix updating user budget across multiple instances by @krrishdholakia in #10993
• Improve response_id propagation logic and add tests for valid/empty I… by @daarko10 in #11006
• Support vertex_ai global endpoints for chat by @sorenmat in #10658
• Ollama wildcard support by @matthid in #10982
• Spend rounded to 4 decimal points on Teams page by @NANDINI-star in #11013
• Place organization and team create buttons at the top by @NANDINI-star in #10948
• Feat: add xai/grok-3 pricing by @ishaan-jaff in #11028
• [Feat] Add Image Edits Support to LiteLLM by @ishaan-jaff in #11020
• Updating the available VoyageAI models in the docs by @fzowl in #11003
• Fix UI - Call tool renders correctly when no arguments required by @wagnerjt in #11012
• Verbose error on admin add by @jugaldb in #10978
• Spend rounded to 4 for Organizations and Users page by @NANDINI-star in #11023
• Fix: Handle dict objects in Anthropic streaming response by @jgowdy-godaddy in #11032
• feat: add Databricks Llama 4 Maverick model cost by @bepotp in #11008
• Add LiteLLM Managed Files support for finetuning api create endpoint by @krrishdholakia in #11039
• Fixes the InvitationLink Prisma find_many query by @jmorenoc-o in #11031
• Support passing prompt_label to langfuse + Log consistent modelParams to langfuse by @krrishdholakia in #11018
• Fix CI | Added closing tags for + indentation changes by @NANDINI-star in #11046
• Feat: add MCP to Responses API and bump openai python sdk by @ishaan-jaff in #11029
• Model filter on logs by @NANDINI-star in #11048
• [Feat] Add claude-4 model family by @ishaan-jaff in #11060
• Litellm managed file updates combined by @krrishdholakia in #11040
• [Fix] Reliability Fix - Removing code that was creating threads on errors by @ishaan-jaff in #11066
• [Feat] Add Azure AD certificate-based authentication by @ishaan-jaff in #11069
• Update feature_request.yml by @ishaan-jaff in #11078
• adds tzdata (#10796) by @krrishdholakia in #11052
• Fix proxy_cli.py: avoid overriding DATABASE_URL when it’s already provided by @martin-liu in #11076
• feat(helm): Add loadBalancerClass support for LoadBalancer services by @gunjan-solanki in #11064
• Add Azure Mistral Medium 25.05 by @emerzon in #11063
• fix:Databricks Claude 3.7 Sonnet output token cost: $17.85/M by @bepotp in #11007
• Fix/openrouter stream usage id 8913 by @daarko10 in #11004
• feat: add embeddings to CustomLLM by @tokoko in #10980
• Enable switching between custom auth and litellm api key auth + Fix /customer/update for max budgets by @krrishdholakia in #11070
• Validate if user can call retrieve + list + delete file by @krrishdholakia in #11081
• [feature] ConfidentAI logging enabled for proxy and sdk by @spike-spiegel-21 in #10649
• Proper github images by @kreatoo in #10927
• Add devstral-small-2505 model to pricing and context window configuration by @xingyaoww in #11103
• [Ci/CD] use n 4 for mapped tests by @ishaan-jaff in #11109
• Fix/background health check by @baejooc in #10887
• [Feat] Add content policy violation error mapping for image edits by @ishaan-jaff in #11113
• Expose /list and /info endpoints for Audit Log events by @krrishdholakia in #11102
• [Feat] Use aiohttp transport by default - 97% lower median latency by @ishaan-jaff in #11097
• Logfire - fix(opentelemetry.py): Fix otel proxy server initialization + Return abbreviated key in key not found error (easier clientside debugging) + Ignore invalid deployments on router load by @krrishdholakia in #11091
• feat(handle_jwt.py): map user to team when added via jwt auth by @krrishdholakia in #11108
• fix(ui_sso.py): maintain backwards compatibility for older user id formats + fix existing user email w/ trailing whitespace check + ensure default_internal_user_settings runs on all user new calls by @krrishdholakia in #11106
• fix(route_llm_request.py): map team model from list in route llm request by @krrishdholakia in #11111
• Remove + Check for unsafe enterprise/ folder imports by @krrishdholakia in #11107
• Fix: Add Claude Sonnet 4 and Opus 4 support for reasoning_effort parameter by @keykbd in #11114
• fix(session): correctly place litellm_session_id at root level instead of metadata by @dalssoft in #11088
• fix(model_management_endpoints): clear cache and reload models after update by @jtong99 in #10853
• [Feat] Add /image/edits on LiteLLM by @ishaan-jaff in #11123
• Correctly delete team model alias when team only model is deleted (#… by @krrishdholakia in #11121
• fix: detect and return status codes in streaming responses by @aholmberg in #10962
• Fix passing standard optional params by @krrishdholakia in #11124
• UI QA fix: team viewer should not see create team by @ishaan-jaff in #11127
• [Chore]: feature flag aiohttp transport - users should opt into using aiohttp transport by @ishaan-jaff in #11132

New Contributors

• @DarinVerheijke made their first contribution in #10596
• @estsauver made their first contribution in #10929
• @mohittalele made their first contribution in #10665
• @pselden made their first contribution in #10899
• @unrealandychan made their first contribution in #10842
• @dastaiger made their first contribution in #10946
• @slytechnical made their first contribution in #10881
• @daarko10 made their first contribution in #11006
• @sorenmat made their first contribution in #10658
• @matthid made their first contribution in #10982
• @jgowdy-godaddy made their first contribution in #11032
• @bepotp made their first contribution in #11008
• @jmorenoc-o made their first contribution in #11031
• @martin-liu made their first contribution in #11076
• @gunjan-solanki made their first contribution in #11064
• @tokoko made their first contribution in #10980
• @spike-spiegel-21 made their first contribution in #10649
• @kreatoo made their first contribution in #10927
• @baejooc made their first contribution in #10887
• @keykbd made their first contribution in #11114
• @dalssoft made their first contribution in #11088
• @jtong99 made their first contribution in #10853

Full Changelog: v1.70.1-stable...v1.71.1-stable

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.71.1-stable

Don't want to maintain your internal proxy? get in touch 🎉

Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results

Name	Status	Median Response Time (ms)	Average Response Time (ms)	Requests/s	Failures/s	Request Count	Failure Count	Min Response Time (ms)	Max Response Time (ms)
/chat/completions	Passed ✅	240.0	263.6638257227686	6.14646557727057	0.0	1836	0	214.31386400001884	1550.7054530000062
Aggregated	Passed ✅	240.0	263.6638257227686	6.14646557727057	0.0	1836	0	214.31386400001884	1550.7054530000062