Starstruk Logo MarkStarstruk

v1.81.10-nightly

BerriAI/litellmv1.81.10-nightlyFeb 11, 2026by github-actions[bot]

AI Summary

This nightly release integrates numerous fixes, new model support, and documentation updates. It focuses on UI improvements, security patches for CVEs, and adds support for new AI providers like Sarvam AI and Perplexity Research.

Key Highlights

  • New model support: Sarvam AI STT/TTS, Kimi k2.5, Perplexity Research API, and Anthropic Claude 4-6.
  • Security: Critical CVE vulnerabilities fixed.
  • UI improvements: Fixed logs copying, team info display, and added predefined error codes in filters.
  • Streaming: Preserved interleaved thinking and redacted thinking blocks during streaming.

New Features

  • Support for anthropic_messages call type in prompt caching.
  • Websearch support using LiteLLM /search interception hook.
  • MCP OAuth2 fixes including M2M support.
  • Output config as a supported parameter.
  • Vercel AI Anthropic models support.

Full Release Notes

## What's Changed
* merge main by @Sameerlite in https://github.com/BerriAI/litellm/pull/20252
* [Docs] 1.81.9 stability by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20665
* Semantic filter hook warning by @krrishdholakia in https://github.com/BerriAI/litellm/pull/20651
* Litellm docs rc fixes  by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20667
* [Bug] PostHog JSON serialization error for non-serializable objects by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/20668
* Observatory block post update by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/20670
* [Docs] UI Team Soft Budget by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20669
* [Docs] UI Contributing and Troubleshooting by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20674
* [Docs] Reorganize Admin UI Subsection by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20676
* docs: add LiteLLM Observatory section to v1.81.9 release notes by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/20675
* [Refactor] Add knip and removed some unused files  by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20678
* [Fix] UI - Logs: Input and Output Copying by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20657
* docs: add callback registration optimization to v1.81.9 release notes by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/20681
* docs: add middleware performance blog post by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/20677
* [Fix] UI - Teams: Available Teams by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20682
* [Refactor] AntD refactoring and 0 cost models fix by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20687
* fix: empty guardrails/policies arrays should not trigger enterprise license check by @veeceey in https://github.com/BerriAI/litellm/pull/20567
* fix critical CVE vulnerabliltes by @Harshit28j in https://github.com/BerriAI/litellm/pull/20683
* Correct ElevenLabs support status in README by @iver56 in https://github.com/BerriAI/litellm/pull/20643
* fix: add hook to handle db case by @Harshit28j in https://github.com/BerriAI/litellm/pull/20635
* Add team policy mapping for zguard by @jwang-gif in https://github.com/BerriAI/litellm/pull/20608
* feat: add support for anthropic_messages call type in prompt caching by @nuernber in https://github.com/BerriAI/litellm/pull/19233
* docs: add SDK proxy authentication (OAuth2/JWT auto-refresh) by @Chesars in https://github.com/BerriAI/litellm/pull/20680
* Fix Bedrock Claude Opus 4.6 model ID (remove :0 suffix) by @veeceey in https://github.com/BerriAI/litellm/pull/20671
* OCI: Cohere responseFormat/Pydantic  by @gotsysdba in https://github.com/BerriAI/litellm/pull/20663
* fix: show error details instead of 'Data Not Available' for failed requests by @veeceey in https://github.com/BerriAI/litellm/pull/20656
* fix(ui): add null guard for models in API keys table by @veeceey in https://github.com/BerriAI/litellm/pull/20655
* Fix: Spend logs pickle error with Pydantic models and redaction by @veeceey in https://github.com/BerriAI/litellm/pull/20685
* fix(vertex_ai): propagate extra_headers anthropic-beta to
 request body by @eliasaronson in https://github.com/BerriAI/litellm/pull/20666
* fix(responses): preserve tool call argument deltas when streaming id is omitted by @emerzon in https://github.com/BerriAI/litellm/pull/20712
* add missing indexes on VerificationToken table by @CAFxX in https://github.com/BerriAI/litellm/pull/20736
* merge main by @Sameerlite in https://github.com/BerriAI/litellm/pull/20738
* fix(streaming): preserve interleaved thinking/redacted_thinking blocks by @emerzon in https://github.com/BerriAI/litellm/pull/20702
* Fix video list pagination cursors not encoded with provider metadata by @tsachis in https://github.com/BerriAI/litellm/pull/20710
* Litellm oss staging 02 08 2026 by @krrishdholakia in https://github.com/BerriAI/litellm/pull/20696
* Add output_config as supported param by @Sameerlite in https://github.com/BerriAI/litellm/pull/20748
* Add new vercel ai anthropic models by @Sameerlite in https://github.com/BerriAI/litellm/pull/20745
* [Feat]Add new claude 4-6 feat for v1/messages by @Sameerlite in https://github.com/BerriAI/litellm/pull/20733
* Fix: get_supported_anthropic_messages_params by @Sameerlite in https://github.com/BerriAI/litellm/pull/20752
* Fix: base_model name for body and deplyment name in URL by @Sameerlite in https://github.com/BerriAI/litellm/pull/20747
* [Feat] Chat completion - Add Websearch support using LiteLLM /search (using web search interception hook) by @Sameerlite in https://github.com/BerriAI/litellm/pull/20483
* fix conflicts with main- (this PR is from upstream/main) by @Harshit28j in https://github.com/BerriAI/litellm/pull/20601
* docs fix. -fwd client headers to LLM API by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20768
* [Feature] UI - Logs: Show Predefined Error Codes in Filter with User Definable Fallback by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20773
* fix(callbacks): allow MAX_CALLBACKS override via env var by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20781
* [Refactor] UI - Remove unused files + Add unit tests by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20780
* [Refactor] UI - Team Info: Migrate to AntD Tabs + Table by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20785
* fix(prometheus): sanitize label values to prevent metric scrape failures by @michelligabriele in https://github.com/BerriAI/litellm/pull/20600
* [Feat] MCP Oauth2 Fixes - Add support for MCP M2M Oauth2 support by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20788
* [Feature] UI - Invite User: Email Integration Alert by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/20790
* [UI] M2M OAuth2 UI Flow  by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/20794
* [Fix] prevent shared backend model key from being polluted by per-deployment custom pricing by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/20679
* fix(mcp): resolve OAuth2 root endpoints returning "MCP server not found" by @michelligabriele in https://github.com/BerriAI/litellm/pull/20784
* fix: Preserved nullable object fields by carrying schema properties by @Sameerlite in https://github.com/BerriAI/litellm/pull/19132
* Add support for langchain_aws via litellm passthrough by @Sameerlite in https://github.com/BerriAI/litellm/pull/20843
* Litellm oss staging 02 05 2026 3 by @Sameerlite in https://github.com/BerriAI/litellm/pull/20854
* feat: Add Sarvam AI STT and TTS support by @NirantK in https://github.com/BerriAI/litellm/pull/19656
* litellm oss staging 09/02/2026 by @krrishdholakia in https://github.com/BerriAI/litellm/pull/20783
* Add Kimi model pricing by region by @Sameerlite in https://github.com/BerriAI/litellm/pull/20855
* Add moonshotai.kimi-k2.5 by @Sameerlite in https://github.com/BerriAI/litellm/pull/20863
* Add support managed error file by @Sameerlite in https://github.com/BerriAI/litellm/pull/20838
* [Feat] Perplexity research api support by @Sameerlite in https://github.com/BerriAI/litellm/pull/20860
* Handle image in assitant message for gemini by @Sameerlite in https://github.com/BerriAI/litellm/pull/20845

## New Contributors
* @iver56 made their first contribution in https://github.com/BerriAI/litellm/pull/20643
* @eliasaronson made their first contribution in https://github.com/BerriAI/litellm/pull/20666
* @NirantK made their first contribution in https://github.com/BerriAI/litellm/pull/19656

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.81.9-nightly...v1.81.10-nightly