Starstruk Logo MarkStarstruk

v1.81.9-nightly

BerriAI/litellmv1.81.9-nightlyFeb 7, 2026by github-actions[bot]

AI Summary

A nightly build preceding the release candidate, featuring significant overlap with the RC including Claude 4.6 support, UI refactoring, and performance optimizations.

Key Highlights

  • Claude Opus 4.6 support across multiple platforms.
  • UI Refactoring: Migration of Admin UI to AntD Tabs.
  • ElevenLabs model support (eleven_v3 and eleven_multilingual_v2).
  • Performance optimization for Prometheus metrics.

New Features

  • ElevenLabs eleven_v3 and eleven_multilingual_v2 support.
  • Soft budget to Team Table.
  • MCP Gateway private/public availability settings.

Full Release Notes

## What's Changed
* fix: search tools not found when using per-request routers by @Quentin-M in https://github.com/BerriAI/litellm/pull/19818
* feat: add faster linting targets for development workflow by @jquinter in https://github.com/BerriAI/litellm/pull/19729
* Litellm fix langfuse otel trace by @Harshit28j in https://github.com/BerriAI/litellm/pull/20382
* fix: Preserve streaming content on guardrail-sampled chunks by @akraines in https://github.com/BerriAI/litellm/pull/20027
* [Fix] Unique Constraint on Daily Tables + Logging When Updates Fail by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20394
* [Feature] UI - Search Tools: Show Config Defined Search Tools by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20436
* Fix mypy regression: TypedDict key error in fireworks_ai transformation by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20391
* langfuse doc update by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/20443
* fix(a2a): use text/event-stream SSE format for message/stream endpoint by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20365
* Revert "fix(a2a): use text/event-stream SSE format for message/stream endpoint" by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20446
* [Fix] inconsistent response format in anthropic.messages.acreate() when using non anthropic providers  by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20442
* [Feat] UI - Add support for MCP Semantic Filtering on UI by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20454
* docs: improve Okta SSO setup guide with step-by-step instructions by @michelligabriele in https://github.com/BerriAI/litellm/pull/20353
* fix(lint): remove unused Any/cast imports in github_copilot transformation by @jquinter in https://github.com/BerriAI/litellm/pull/20431
* feat(openrouter): add Qwen3-235B models by @Chesars in https://github.com/BerriAI/litellm/pull/20455
* bump: litellm-proxy-extras 0.4.29 → 0.4.30 by @Sameerlite in https://github.com/BerriAI/litellm/pull/20458
* chore: update poetry.lock for litellm-proxy-extras 0.4.30 by @Sameerlite in https://github.com/BerriAI/litellm/pull/20460
* [Infra] Fixing UI Build by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20461
* Litellm cicd 5 feb 2026 by @Sameerlite in https://github.com/BerriAI/litellm/pull/20464
* bugfix: Disable merging of consecutive user messages for GigaChat provider by @natimofeev in https://github.com/BerriAI/litellm/pull/20341
* Fix Vertex AI Gemini streaming content_filter handling by @krisxia0506 in https://github.com/BerriAI/litellm/pull/20105
* fix #20326 - [Feature]: Support TTL(1h) field in prompt caching for Bedrock Claude 4.5 models  by @Lucky-Lodhi2004 in https://github.com/BerriAI/litellm/pull/20338
* Litellm oss staging 02 04 2026 by @krrishdholakia in https://github.com/BerriAI/litellm/pull/20398
* Cli arguments rds iam auth by @krrishdholakia in https://github.com/BerriAI/litellm/pull/20437
* [Fix] 404 Not Found on /api/event_logging/batch endpoint  by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20504
* [Feat] add `claude-opus-4-6` to model cost map by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20506
* Add Claude Opus 4.6 by @PeterDaveHello in https://github.com/BerriAI/litellm/pull/20508
* fix(ui): adjust daily spend date filtering for user timezone by @nina-hu in https://github.com/BerriAI/litellm/pull/20472
* [Fix] Non Root Dockerfile: Keep package-lock.json by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20452
* [Infra] UI - Adding Unit Tests for Coverage by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20513
* Fix test isolation for test_watsonx_gpt_oss_prompt_transformation by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20474
* Fix test isolation for test_log_langfuse_v2_handles_null_usage_values by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20475
* [Fix] Guardrails API - Ensure OpenAI Moderations Guard works with OpenAI Embeddings  by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20523
* [Feature] Add soft_budget to Team Table + Create/Update Endpoints by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20530
* [Chore] Move anthropic input/output test to right folder by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/20535
* [Refactor] UI - Usage Page: Spend By Provider by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20539
* fix: make sure gcs_bucket_name passes by @Sameerlite in https://github.com/BerriAI/litellm/pull/20491
* feat(web_search): add gpt-5-search-api model and docs clarifications by @Chesars in https://github.com/BerriAI/litellm/pull/20512
* [Feat] add ElevenLabs eleven_v3 and eleven_multilingual_v2 to model cost map by @Chesars in https://github.com/BerriAI/litellm/pull/20522
* [Refactor] UI - Admin Page: Migrate to AntD Tabs by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20465
* fix: Add array type checks for model, agent, and MCP hub data to prev… by @swayambhu94 in https://github.com/BerriAI/litellm/pull/20469
* [Refactor] Rename admins to AdminPanel by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20554
* Align Claude Opus 4.6 metadata and limits by @PeterDaveHello in https://github.com/BerriAI/litellm/pull/20514
* Add unsupported claude code beta headers in json by @Sameerlite in https://github.com/BerriAI/litellm/pull/20578
* Add full support  for Opus 4.6 (Anthropic, Azure AI, Bedrock, Vertex AI) by @Sameerlite in https://github.com/BerriAI/litellm/pull/20551
* perf(prometheus): parallelize budget metrics, fix caching bug, reduce CPU by ~40% by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/20544
* Warn when budget lookup fails; cache won't populate by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/20545
* [Feature] Team Soft Budget Email Alerts by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20553
* Add INFO-level session reuse logging per request by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/20597
* [Infra] UI - Testing: Adding Unit Testing Coverage by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20596
* [Feature] UI - Admin Settings: Add option for Authentication for public AI Hub by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20444
* [Fix] UI - Model Info Page: Fix Input and Output Labels by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20462
* [Fix] UI - Model Page: Column Resizing on Smaller Screens by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20599
* refactor: migrate Ant Design notifications to use `App.useApp()` cont… by @swayambhu94 in https://github.com/BerriAI/litellm/pull/20549
* fix(mcp): resolve OAuth2 'Capabilities: none' bug for upstream MCP servers by @michelligabriele in https://github.com/BerriAI/litellm/pull/20602
* [Fix] A2a Agent Gateway Fixes - A2A agents deployed with localhost/internal URLs in their agent cards (e.g., http://0.0.0.0:8001/) by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20604
* [Re-issue: Fix] Keys and Teams Router Setting + Allow Override of Router Settings by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20205
* fix(sso): extract user roles from JWT access token for Keycloak compa… by @michelligabriele in https://github.com/BerriAI/litellm/pull/20591
* [Feat] add au version of `claude-opus-4-6` to model cost map by @ssadedin in https://github.com/BerriAI/litellm/pull/20566
* Add http support to custom code guardrails + Unified guardrails for MCP + Agent guardrail support by @krrishdholakia in https://github.com/BerriAI/litellm/pull/20619
* fix(mypy): resolve missing return statements and type casting issues by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20618
* [Feat] MCP Gateway - Allow setting MCP Servers as Private/Public available on Internet by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20607
* [Feat] IP-Based Access Control for MCP Servers by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20620
* Add blog post about litellm-observatory by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/20622
* [Fix] /key/list user_id Empty String Edge Case by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20623
* docs - expose MCPs on public internet  by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20626
* fix(mypy): Stabilize mypy linting - resolve type checking errors by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20627
* fix(test): update deprecated gemini embedding model by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20621
* [Feature] UI - Team Settings: Soft Budget + Alerting Emails by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20634
* Update opus 4.6 blog with adaptive thinking by @Sameerlite in https://github.com/BerriAI/litellm/pull/20637
* [Infra] UI Build for Release by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20648
* fix(lint): extract helper function to reduce statement count in MCP rest_endpoints by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20629
* perf: add LRU cache to normalize_request_route by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/19812
* fix(tests): Fix sendgrid email tests to properly mock httpx client by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20628
* perf: optimize get_standard_logging_metadata with set intersection by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/19685
* fix(tests): Fix flaky container and scientific notation tests by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20650
* perf: add early-exit guards in completion_cost for unused features by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/20020
* perf: Optimize get_litellm_params with sparse kwargs extraction by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/19884
* perf: guard debug log f-strings and remove redundant dict copy by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/19961
* perf: replace enum construction with frozenset lookup by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/20302
* perf: guard debug f-string in update_environment_variables by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/20360
* fixes content blocked by bedrock by @Harshit28j in https://github.com/BerriAI/litellm/pull/20606
* [Infra] Deleted Teams Table soft_budget by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20653
* perf: optimize should_run_callback() by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/20449
* fix(tests): Add missing mocks for MCP IP filtering and updated APIs by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20652
* Revert "perf: optimize should_run_callback()" by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20659
* fix(proxy): only create Router when models or search_tools exist by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20661

## New Contributors
* @Quentin-M made their first contribution in https://github.com/BerriAI/litellm/pull/19818
* @nina-hu made their first contribution in https://github.com/BerriAI/litellm/pull/20472
* @swayambhu94 made their first contribution in https://github.com/BerriAI/litellm/pull/20469
* @ssadedin made their first contribution in https://github.com/BerriAI/litellm/pull/20566

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.81.7.dev1...v1.81.9-nightly