v1.81.14.rc.1

📅 Feb 23, 2026📦 litellmView on GitHub →

✨ 15 features🐛 34 fixes🔧 25 symbols

Summary

This release introduces significant feature additions, including Gemini 3.1 Pro preview support, new AI policy templates, and method-based routing for passthrough endpoints. Numerous bug fixes address issues across proxying, Bedrock integration, Anthropic translation, and CI/testing stability.

Migration Steps

If you rely on CI workflows that regenerate poetry.lock, note that the --no-update flag has been removed in Poetry 2.x and CI logic has been updated to accommodate this.
If you were using the COMPETITOR_LLM_TEMPERATURE or MAX_COMPETITOR_NAMES environment variables, they can now be overridden via environment variables.

✨ New Features

[Feat] Add Default usage data configuration
[Feat] Add server side compaction translation from openai to anthropic
Add method based routing for passthrough endpoints
[Feat]Add gemini 3.1 pro preview day 0 support
[Feature] Key Last Active Tracking
feat: AI policy template suggestions
Add OpenAPI-to-MCP support via API and UI
feat: add airline off-topic restriction policy template
feat(policy): test playground for AI policy suggestions
feat: prompt injection guardrail policy template
feat(ui): show latency overhead for AI-suggested policy templates
feat(ci): auto-approve and auto-merge the regenerated poetry.lock PR
support reasoning and effort parameters on sonnet 4.6
[Feat] Add reasoning support via config
[Fix]Add mcp via openapi spec

🐛 Bug Fixes

fix: remove list-to-str transformation from dashscope
Uncomment response_model in user_info endpoint
fix: allow github aliases to reuse upstream model metadata
fix(proxy): prevent is_premium() debug log spam on every request
Convert thinking_blocks to content blocks for hosted_vllm multi-turn
Fix usage in xai
Fix: add stop param as supported for openai and azure
fix(websearch_interception): fix pre_call_deployment_hook not triggering via proxy router
fix(constants): add env var override support for COMPETITOR_LLM_TEMPERATURE and MAX_COMPETITOR_NAMES
fix(types): fix mypy errors in pass-through endpoint query param types
fix: handle deprovisioning operations without path field
fix(bedrock): add Accept header for AgentCore MCP server requests
fix: reduce proxy overhead for large base64 payloads
fix(key management): return failed_tokens in delete_verification_tokens response
fix(ci): fix YAML syntax error in regenerate-poetry-lock workflow
fix(ci): fall back to github.token when GH_TOKEN secret is not set
fix(ci): remove --no-update flag removed in Poetry 2.x
fix(ci): use PAT_TOKEN_2 for gh pr create in regenerate-lock workflow
fix(ci): drop PAT_TOKEN_2 approval, use github.token for auto-merge
[Fix] Service Account Visibility for Team Members
fix: handle explicit None model_info in LowestLatencyLoggingHandler
fix(lint): remove unused imports in semantic_guard and policy_endpoints
fix(tests): set premium_user=True in JWT tests that call user_api_key_auth
fix(anthropic): empty system messages in translate_system_message
fix(tests): pass host to RedisCache in test_team_update_redis
fix(policy): use litellm.acompletion directly in AiPolicySuggester
fix(lint): remove redundant router import in policy_endpoints __init__
Fix _map_reasoning_effort_to_thinking_level for all gemini 3 family
Fix: api_base is required. Unable to determine the correct api_base for the request
Fix mapping of parallel_tool_calls for bedrock converse
fix(tests): update test_max_effort_rejected_for_opus_45 regex to match current error message
fix(policy_endpoints): re-export private helper functions from package __init__.py
fix(tests): set premium_user=True in test_aasync_call_with_key_over_model_budget
fix(tests): correct medium reasoning_effort assertion for gemini-3-pro-preview for gemini-3-pro-preview

Summary

Migration Steps

✨ New Features

🐛 Bug Fixes

Affected Symbols