litellm changelog and release notes, page 13

1.82.110 Mar 2026Security

Doc: security vulnerability scan report to v1.81.14 release notes by @Harshit28j in https://github.com/BerriAI/litellm/pull/22385

What's Changed

fix(gemini): preserve $ref in JSON Schema for Gemini 2.0+ by @Chesars in https://github.com/BerriAI/litellm/pull/21597
fix(transcription): move duration to _hidden_params to match OpenAI response spec by @Chesars in https://github.com/BerriAI/litellm/pull/22208
fix(anthropic): map reasoning_effort to output_config for Claude 4.6 models by @Chesars in https://github.com/BerriAI/litellm/pull/22220
feat(vertex): add gemini-3.1-flash-image-preview to model DB by @emerzon in https://github.com/BerriAI/litellm/pull/22223
perf(spendlogs): optimize old spendlog deletion cron job by @Harshit28j in https://github.com/BerriAI/litellm/pull/21930
Fix converse handling for parallel_tool_calls by @Sameerlite in https://github.com/BerriAI/litellm/pull/22267
[Fix]Preserve forwarding server side called tools by @Sameerlite in https://github.com/BerriAI/litellm/pull/22260
Fix free models working from UI by @Sameerlite in https://github.com/BerriAI/litellm/pull/22258
Add v1 for anthropic responses transformation by @Sameerlite in https://github.com/BerriAI/litellm/pull/22087
[Bug]Add ChatCompletionImageObject in OpenAIChatCompletionAssistantMessage by @Sameerlite in https://github.com/BerriAI/litellm/pull/22155
Fix: poetry lock by @Sameerlite in https://github.com/BerriAI/litellm/pull/22293
Enable local file support for OCR by @noahnistler in https://github.com/BerriAI/litellm/pull/22133
fix(mcp): Strip stale mcp-session-id to prevent 400 errors across proxy workers by @gavksingh in https://github.com/BerriAI/litellm/pull/21417
[Feature] Access group CRUD: Bidirectional team/key sync by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22253
Add LLMClientCache regression tests for httpx client eviction safety by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22306
fix(images): forward extra_headers on OpenAI code path in image_generation() by @Chesars in https://github.com/BerriAI/litellm/pull/22300
feat(models): add gpt-audio-1.5 to model cost map by @Chesars in https://github.com/BerriAI/litellm/pull/22303
feat(models): add gpt-realtime-1.5 to model cost map by @Chesars in https://github.com/BerriAI/litellm/pull/22304
fix(images): pass model_info/metadata in image_edit for custom pricing by @Chesars in https://github.com/BerriAI/litellm/pull/22307
fix(chatgpt): fix tool_calls streaming indexes by @Chesars in https://github.com/BerriAI/litellm/pull/21498
fix(openai): correct supported_openai_params for GPT-5 model family by @Chesars in https://github.com/BerriAI/litellm/pull/21576
fix(openai): correct supported params for gpt-5-search models by @Chesars in https://github.com/BerriAI/litellm/pull/21574
fix(azure_ai): resolve api_base from env var in Document Intelligence OCR by @Chesars in https://github.com/BerriAI/litellm/pull/21581
fix(models): function calling for PublicAI Apertus models by @Chesars in https://github.com/BerriAI/litellm/pull/21582
fix(vertex_ai): pass through native Gemini imageConfig params for image generation by @Chesars in https://github.com/BerriAI/litellm/pull/21585
fix(openrouter): use provider-reported usage in streaming without stream_options by @Chesars in https://github.com/BerriAI/litellm/pull/21592
fix(moonshot): preserve image_url blocks in multimodal messages by @Chesars in https://github.com/BerriAI/litellm/pull/21595
fix(types): remove StreamingChoices from ModelResponse, use ModelResponseStream by @Chesars in https://github.com/BerriAI/litellm/pull/21629
fix(responses): use output_index for parallel tool call streaming indices by @Chesars in https://github.com/BerriAI/litellm/pull/21337
Tests: add llmclientcache regression tests by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22313
Add deprecation dates for xAI grok-2-vision-1212 and grok-3-mini models by @Chesars in https://github.com/BerriAI/litellm/pull/20102
fix(containers): Fix Python 3.10 compatibility for OpenAIContainerConfig by @Chesars in https://github.com/BerriAI/litellm/pull/19786
fix(count_tokens): include system and tools in token counting API requests by @Chesars in https://github.com/BerriAI/litellm/pull/22301
fix(helicone): add Gemini and Vertex AI support to HeliconeLogger by @Chesars in https://github.com/BerriAI/litellm/pull/19288
fix(register_model): handle openrouter models without '/' in name by @Chesars in https://github.com/BerriAI/litellm/pull/19792
feat(model_prices): add OpenRouter native models to model cost map by @Chesars in https://github.com/BerriAI/litellm/pull/20520
fix(adapter): double-stripping of model names with provider-matching prefixes by @Chesars in https://github.com/BerriAI/litellm/pull/20516
docs: add OpenRouter Opus 4.6 to model map and update Claude Opus 4.6 docs by @Chesars in https://github.com/BerriAI/litellm/pull/20525
[Fix] Include timestamps in /project/list response by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22323
[Feature] UI - Projects: Add Projects page with list and create flows by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22315
Fix/claude code plugin schema by @rahulrd25 in https://github.com/BerriAI/litellm/pull/22271
Add Prometheus child_exit cleanup for gunicorn workers by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22324
docs: update AssemblyAI docs with Universal-3 Pro, Speech Understanding, and LLM Gateway by @dylan-duan-aai in https://github.com/BerriAI/litellm/pull/21130
feat: add in_flight_requests metric to /health/backlog + prometheus by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22319
fix(test): update realtime guardrail test assertions for voice violation behavior by @jquinter in https://github.com/BerriAI/litellm/pull/22332
fix(test): update Azure pass-through test after Responses API routing change by @jquinter in https://github.com/BerriAI/litellm/pull/22334
fix(db): add missing migration for LiteLLM_ClaudeCodePluginTable by @jquinter in https://github.com/BerriAI/litellm/pull/22335
fix(bedrock): restore parallel_tool_calls mapping in map_openai_params by @jquinter in https://github.com/BerriAI/litellm/pull/22333
[Feat] Agent RBAC Permission Fix - Ensure Internal Users cannot create agents by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22329
fix(mcp): update test mocks for renamed filter_server_ids_by_ip_with_info by @jquinter in https://github.com/BerriAI/litellm/pull/22327
fix: Add PROXY_ADMIN role to system user for key rotation by @milan-berri in https://github.com/BerriAI/litellm/pull/21896
fix: populate user_id and user_info for admin users in /user/info by @milan-berri in https://github.com/BerriAI/litellm/pull/22239
fix(caching): store task references in LLMClientCache._remove_key by @shivaaang in https://github.com/BerriAI/litellm/pull/22143
fix(image_generation): propagate extra_headers to Upstream by @ZeroClover in https://github.com/BerriAI/litellm/pull/22026
[Fix] Pass MCP auth headers from request into tool fetch for /v1/responses and chat completions by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/22291
fix: shorten guardrail benchmark result filenames for Windows long path support by @demoray in https://github.com/BerriAI/litellm/pull/22039
Remove Apache 2 license from SKILL.md by @rasmi in https://github.com/BerriAI/litellm/pull/22322
fix(mcp): default available_on_public_internet to true by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22331
fix(bedrock): filter internal json_tool_call when mixed with real tools by @jquinter in https://github.com/BerriAI/litellm/pull/21107
fix(jwt): OIDC discovery URLs, roles array handling, dot-notation error hints by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22336
perf: streaming latency improvements — 4 targeted hot-path fixes by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22346
[Test] UI - CostTrackingSettings: Add comprehensive Vitest coverage by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22354
[Feature] Key list endpoint: Add project_id and access_group_id filters by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22356
[Feature] UI - Projects: Add Project Details Page by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22360
[Feature] UI - Projects: Add project keys table and project dropdown to key create/edit by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22373
Litellm health check tokens by @Harshit28j in https://github.com/BerriAI/litellm/pull/22299
Doc: security vulnerability scan report to v1.81.14 release notes by @Harshit28j in https://github.com/BerriAI/litellm/pull/22385
feat: ability to trace metrics datadog by @Harshit28j in https://github.com/BerriAI/litellm/pull/22103
feat(ci): add duplicate issue detection and auto-close bot by @jquinter in https://github.com/BerriAI/litellm/pull/22034
Litellm aws edge case by @Harshit28j in https://github.com/BerriAI/litellm/pull/22384
Litellm presidio stream v3 by @Harshit28j in https://github.com/BerriAI/litellm/pull/22283
fix: update_price_and_context_window workflow from running in forks by @Chesars in https://github.com/BerriAI/litellm/pull/18478
fix(ci): remove duplicate env key in scan_duplicate_issues workflow by @Chesars in https://github.com/BerriAI/litellm/pull/22405
fix(lint): suppress PLR0915 in complex transform methods by @jquinter in https://github.com/BerriAI/litellm/pull/22328
fix: atomic RPM rate limiting in model rate limit check by @jquinter in https://github.com/BerriAI/litellm/pull/22002
test(ci): add secret scan test and CI job by @jquinter in https://github.com/BerriAI/litellm/pull/22193
fix(proxy): isolate get_config failures from model sync loop by @jquinter in https://github.com/BerriAI/litellm/pull/22224
fix tts metrics issues by @Harshit28j in https://github.com/BerriAI/litellm/pull/20632
[Release Fix] by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22411
fix(ci): handle inline table in pyproject.toml for proxy-extras version check by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22414
[Feature] UI - Projects: Add delete project action by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22412
fix: bump litellm-proxy-extras to 0.4.50 and fix 3 failing tests by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22417
[Fix] UI - resolve flaky tests from leaked @tremor/react Tooltip timer by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22420
[Feature] UI - Admin Settings: Projects Opt-In Toggle by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22416
[Infra] Building UI for Release by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22423
fix(mypy): fix 3 mypy/pyright errors in presidio.py and _health_endpoints.py by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22422
bump: litellm-enterprise 0.1.32 → 0.1.33 + manual publish workflow by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22421
fix(mcp): set LITELLM_MASTER_KEY env var in e2e tests by @jquinter in https://github.com/BerriAI/litellm/pull/22413
fix(ci): replace default CodeQL with custom workflow to unblock CI by @jquinter in https://github.com/BerriAI/litellm/pull/22397
Development environment setup by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22432
fix(test): add spend data polling + graceful skip to Gemini e2e spend… by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22446
[Fix] UI - Virtual Keys: Fix beforeunload listener memory leak by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22430
Litellm stability fix v2 by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22452
fix: resolve ruff PLR0915 and mypy type checking lint errors by @anencore94 in https://github.com/BerriAI/litellm/pull/22359
Fix plaintext JWTs leaking in debug logs by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22424
fix(anthropic): populate output_config when reasoning_effort is used on Claude 4.6 by @giulio-leone in https://github.com/BerriAI/litellm/pull/22410
fix: add sync streaming fallback + fix 429 for all streaming paths by @CSteigstra in https://github.com/BerriAI/litellm/pull/22375
fix(vertex_ai): Set anthropic-beta as HTTP header for Vertex AI rawPredict by @castrapel in https://github.com/BerriAI/litellm/pull/22321
fix(types): normalize null top_logprobs to [] in ChatCompletionTokenLogprob by @shivaaang in https://github.com/BerriAI/litellm/pull/22245
fix (model-map): gemini litellm_provider for gemini/gemini-2.5-flash-image by @Dima-Mediator in https://github.com/BerriAI/litellm/pull/22156
fix(ui): Display newlines correctly in tool descriptions by @RussellLuo in https://github.com/BerriAI/litellm/pull/22363
[UI QA] - Add all provider models + providers on ui by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22461
Budget reset times and timezones by @krrishdholakia in https://github.com/BerriAI/litellm/pull/22428
Add OCR guardrail_translation handler support by @krrishdholakia in https://github.com/BerriAI/litellm/pull/22145
[Fix] Invite link allows multiple password resets by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22462
[Docs] Project Management UI by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22472
[Fix] UI - QueryClient: move to single root-level provider by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22463
[Feat] Make UI login session duration configurable via LITELLM_UI_SESSION_DURATION by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/22182
Add observatory test workflow for RC/stable releases by @jquinter in https://github.com/BerriAI/litellm/pull/22508
Fix invalid secrets context in test-linting workflow by @jquinter in https://github.com/BerriAI/litellm/pull/22517
Fix observatory workflow checkout failing on commit hash by @jquinter in https://github.com/BerriAI/litellm/pull/22518
Fix undefined kwargs in InFlightRequestsMiddleware by @jquinter in https://github.com/BerriAI/litellm/pull/22523
Fix observatory tunnel DNS flakiness and PLR0915 lint by @jquinter in https://github.com/BerriAI/litellm/pull/22525
Fix PLR0915 lint error in _completion_streaming_iterator by @jquinter in https://github.com/BerriAI/litellm/pull/22526
fix(featherless_ai): use correct FEATHERLESS_AI_API_KEY env var name by @giulio-leone in https://github.com/BerriAI/litellm/pull/22497
fix(bedrock): extract region and model ID from bedrock/{region}/{model} path format by @Sameerlite in https://github.com/BerriAI/litellm/pull/22546
feat(vertex-ai): add VIDEO modality support in token usage tracking by @Sameerlite in https://github.com/BerriAI/litellm/pull/22550
Litellm oss staging 02 28 2026 by @krrishdholakia in https://github.com/BerriAI/litellm/pull/22340
fix(openrouter): pattern-based fix for native model double-stripping by @tombii in https://github.com/BerriAI/litellm/pull/22320
Revert "fix(adapter): double-stripping of model names with provider-matching prefixes" by @Chesars in https://github.com/BerriAI/litellm/pull/22593
docs: add fallback setup for virtual key with Loom video by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/22600
[Feat] Make MCP timeouts configurable via environment variables by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/22287
feat: add missing Mistral models and update pricing by @Chesars in https://github.com/BerriAI/litellm/pull/22601
fix: add missing pricing for dashscope/qwen3.5-plus and dashscope/qwen3-vl-plus by @Chesars in https://github.com/BerriAI/litellm/pull/22596
fix: update Gemini model deprecation dates by @Chesars in https://github.com/BerriAI/litellm/pull/22586
fix(pricing): add missing cache token pricing for 24 Bedrock Claude models by @Chesars in https://github.com/BerriAI/litellm/pull/22583
Litellm oss staging 02 26 2026 by @Chesars in https://github.com/BerriAI/litellm/pull/22582
Litellm oss staging 02 27 2026 by @Chesars in https://github.com/BerriAI/litellm/pull/22584
Add CrowdStrike AIDR guardrail hook by @kenany in https://github.com/BerriAI/litellm/pull/17876
feat(perplexity): add embedding support for pplx-embed-v1 models by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22610
Pr template test path by @krrishdholakia in https://github.com/BerriAI/litellm/pull/22612
[Feat] Add pricing for Nebius models by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22614
Add incident report: cache eviction closes in-use httpx clients by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22309
fix: set mock status_code in JWT OIDC discovery tests by @anencore94 in https://github.com/BerriAI/litellm/pull/22361
fix(openrouter): register OpenRouter as native Responses API provider by @shivaaang in https://github.com/BerriAI/litellm/pull/22355
feat(guardrails): team-based guardrail registration and approval workflow by @krrishdholakia in https://github.com/BerriAI/litellm/pull/22459
Managed batches fixes for vertex by @ephrimstanley in https://github.com/BerriAI/litellm/pull/22464
feat(togetherai): add support for togetherai/Qwen3.5-397B-A17B model by @Varad2001 in https://github.com/BerriAI/litellm/pull/22654
Revert "feat(togetherai): add support for togetherai/Qwen3.5-397B-A17B model" by @Sameerlite in https://github.com/BerriAI/litellm/pull/22657
bump: version 1.82.0 → 1.82.1 by @Harshit28j in https://github.com/BerriAI/litellm/pull/22631
Fix: Azure ai finetuning api by @Sameerlite in https://github.com/BerriAI/litellm/pull/22625
[Chore]Remove defualt hardcoded thinking levels for gemini 3 family by @Sameerlite in https://github.com/BerriAI/litellm/pull/22641
Add support for encrypted content affinity by @Sameerlite in https://github.com/BerriAI/litellm/pull/22651
fix(pricing): add 5 missing OpenRouter model pricing entries by @Chesars in https://github.com/BerriAI/litellm/pull/22649
fix(pricing): add 7 missing DashScope model pricing entries by @Chesars in https://github.com/BerriAI/litellm/pull/22650
fix(proxy): allow custom auth routes to bypass route authorization ch… by @Harshit28j in https://github.com/BerriAI/litellm/pull/22662
feat(models): add zai/glm-5 and zai/glm-5-code to model cost map by @Chesars in https://github.com/BerriAI/litellm/pull/22665
Day 0 gemini 3.1 flash lite preview support by @Sameerlite in https://github.com/BerriAI/litellm/pull/22674
Add support for Attaching knowledge base to model via UI by @Sameerlite in https://github.com/BerriAI/litellm/pull/22656
[Fix] MCP server: preserve created_at and updated_at timestamps by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22680
fix(proxy): encode batch IDs when x-litellm-model header is used by @Chesars in https://github.com/BerriAI/litellm/pull/22653
chore: update python-multipart constraint to >=0.0.18 by @Chesars in https://github.com/BerriAI/litellm/pull/17308
chore: code duplication in files/main.py using credential helpers by @Chesars in https://github.com/BerriAI/litellm/pull/20920
fix(vertex): preserve type schema semantics for JsonValuefields by @Chesars in https://github.com/BerriAI/litellm/pull/22589
fix(helicone): correct provider URL for Vertex AI Gemini models by @Chesars in https://github.com/BerriAI/litellm/pull/22603
fix(gemini): correct streaming finish_reason for tool calls by @Chesars in https://github.com/BerriAI/litellm/pull/21577
fix(anthropic): remove hardcoded reasoning summary in adapter by @Chesars in https://github.com/BerriAI/litellm/pull/21491
feat: support per-request enable_json_schema_validation for thread safety by @Chesars in https://github.com/BerriAI/litellm/pull/21233
feat(openrouter): add image edit support for OpenRouter models by @shivaaang in https://github.com/BerriAI/litellm/pull/22403
[Fix] Spend Log Cleanup: lock tracking, integer retention, skip log level by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22687
feat: guardrail-mode-default-list by @Harshit28j in https://github.com/BerriAI/litellm/pull/22676
Fix mypy override errors in count_tokens signatures by @jquinter in https://github.com/BerriAI/litellm/pull/22699
[Test] UI - Projects: Add unit tests for project hooks by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22698
Litellm feat batch expiry setting teams by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22705
Fix Anthropic streaming sync and Azure GPT-5.1 logprobs tests by @jquinter in https://github.com/BerriAI/litellm/pull/22701
fix: update vertex AI tests for function_response role=user by @jquinter in https://github.com/BerriAI/litellm/pull/22716
fix: add video_tokens to completion_tokens_details test by @jquinter in https://github.com/BerriAI/litellm/pull/22717
fix: use direct AsyncMock in JWT OIDC discovery tests by @jquinter in https://github.com/BerriAI/litellm/pull/22718
fix: account for vertex_ai schema diff in response_format test by @jquinter in https://github.com/BerriAI/litellm/pull/22719
fix: use real State in mock_request for proxy_utils tests by @jquinter in https://github.com/BerriAI/litellm/pull/22720
[Feature] UI - Virtual Keys: Manual Spend Reset by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22715
fix: resolve base_model in /cost/estimate for Azure custom deployments by @milan-berri in https://github.com/BerriAI/litellm/pull/22724
[Fix] Team Admin Reset Key Spend by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22725
[Fix] UI - Audit Logs: Server-side pagination, filtering, and drawer view by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22476
fix: pass all custom pricing fields to register_model in completion() and embedding() by @shanemort1982 in https://github.com/BerriAI/litellm/pull/22552
Agent Tracing - support context_id based trace id propogation + nested llm calls by @krrishdholakia in https://github.com/BerriAI/litellm/pull/22626
feat(togetherai): add support for TogetherAI Qwen3.5-397B-A17B model by @Varad2001 in https://github.com/BerriAI/litellm/pull/22685
fix: add missing supports_function_calling for deepinfra models by @OiPunk in https://github.com/BerriAI/litellm/pull/22620
Managed batches - Address PR bot comments from #22464 by @ephrimstanley in https://github.com/BerriAI/litellm/pull/22666
[Feat] UI - Add Open in New Tab on leftnav Bar by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22731
[Feat] Add Tool Policies for AI Gateway by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22732
feat(proxy): add key_alias, key_hash, requested_model DD APM span tags by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/22710
Add Support for OpenAI's Chat-GPT 5.3 Chat model by @PeterDaveHello in https://github.com/BerriAI/litellm/pull/22693
[Fix] UI - Tool Policies: Add missing ToolRow properties by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/22739
reusable-credentials by @atapia27 in https://github.com/BerriAI/litellm/pull/22316
virtual-keys-team-table by @atapia27 in https://github.com/BerriAI/litellm/pull/21958
fix(proxy): make common_checks opt-in for custom auth by @Harshit28j in https://github.com/BerriAI/litellm/pull/22678
merge main for 030326 by @Sameerlite in https://github.com/BerriAI/litellm/pull/22765
Revert "fix(anthropic): remove hardcoded reasoning summary in adapter" by @Sameerlite in https://github.com/BerriAI/litellm/pull/22768
Litellm oss staging 03 03 2026 by @Chesars in https://github.com/BerriAI/litellm/pull/22689
chore: regenerate poetry.lock to match pyproject.toml by @github-actions[bot] in https://github.com/BerriAI/litellm/pull/22769
[Feat] Add support for Responses Websocket by @Sameerlite in https://github.com/BerriAI/litellm/pull/22559
feat(tests): add proxy e2e azure batches test by @Sameerlite in https://github.com/BerriAI/litellm/pull/22763
[Feat] Add Google Search API Integration by @Sameerlite in https://github.com/BerriAI/litellm/pull/22752
Add mcp streaming events Fix and consistent response ID by @Sameerlite in https://github.com/BerriAI/litellm/pull/22744
Add support for wildcards models for files api by @Sameerlite in https://github.com/BerriAI/litellm/pull/22740
Fix MCP server URL and tools management by @Sameerlite in https://github.com/BerriAI/litellm/pull/22751
Fix flaky MCP streaming test and iterator silent failure by @jquinter in https://github.com/BerriAI/litellm/pull/22777
Exclude aresponses_websocket from Azure SDK client init test by @jquinter in https://github.com/BerriAI/litellm/pull/22778
Fix A2A message context_id access when message is a dict by @jquinter in https://github.com/BerriAI/litellm/pull/22780
Fix tool management tests using wrong field name call_policy by @jquinter in https://github.com/BerriAI/litellm/pull/22781
Add missing migration for LiteLLM_ToolTable policy changes by @jquinter in https://github.com/BerriAI/litellm/pull/22783
Fix responses ID security test for new request_cache parameter by @jquinter in https://github.com/BerriAI/litellm/pull/22784
Guard tenacity import in e2e Azure batch tests by @jquinter in https://github.com/BerriAI/litellm/pull/22785
Remove incompatible openai==1.100.1 pin from linting CI by @jquinter in https://github.com/BerriAI/litellm/pull/22789
Add tenacity to e2e Azure batch CI and revert importorskip by @jquinter in https://github.com/BerriAI/litellm/pull/22788
fix: remove unused EncryptedContentAffinityCheck import in router.py by @jquinter in https://github.com/BerriAI/litellm/pull/22776
fix: add new model_prices properties to validation schema by @jquinter in https://github.com/BerriAI/litellm/pull/22775
Add support for responses websocket for all providers by @Sameerlite in https://github.com/BerriAI/litellm/pull/22771
fix(proxy): improve team expiry enforcement validation by @ryan-crabbe in https://github.com/BerriAI/litellm/pull/22728
azure content enhancement... by @ma-armenta in https://github.com/BerriAI/litellm/pull/22581
fix(responses): preserve query params when building /responses/compact URL by @SebLz in https://github.com/BerriAI/litellm/pull/22668

New Contributors

@noahnistler made their first contribution in https://github.com/BerriAI/litellm/pull/22133
@dylan-duan-aai made their first contribution in https://github.com/BerriAI/litellm/pull/21130
@rasmi made their first contribution in https://github.com/BerriAI/litellm/pull/22322
@RussellLuo made their first contribution in https://github.com/BerriAI/litellm/pull/22363
@kenany made their first contribution in https://github.com/BerriAI/litellm/pull/17876
@Varad2001 made their first contribution in https://github.com/BerriAI/litellm/pull/22654
@shanemort1982 made their first contribution in https://github.com/BerriAI/litellm/pull/22552
@SebLz made their first contribution in https://github.com/BerriAI/litellm/pull/22668

Full Changelog: https://github.com/BerriAI/litellm/compare/litellm_presidio-dev-v1.81.16...1.82.1

Open source →

1.81.1317 Feb 2026

[Feature] UI - Keys/Teams: Add Access Group Selector to Create and Edit Flow by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21234

What's Changed

[Feature] UI - Keys/Teams: Add Access Group Selector to Create and Edit Flow by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21234
[Fix] Preserve key_alias and team_id metadata in /user/daily/activity/aggregated after key deletion or regeneration by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/20684
[Infra] Fixes + UI Build by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21235
[Docs] Access Group Docs by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21236
[Infra] UI - Unit Tests: Increase timeout on Long Running Tests by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21237
fix: use None instead of Reasoning() for reasoning parameter by @jquinter in https://github.com/BerriAI/litellm/pull/21103
chore: add .claude directory to gitignore by @jquinter in https://github.com/BerriAI/litellm/pull/21104
fix: remove unused Reasoning import from transformation.py by @jquinter in https://github.com/BerriAI/litellm/pull/21246
Fix: Langfuse test isolation to prevent flaky failures by @jquinter in https://github.com/BerriAI/litellm/pull/21214
fix(test): resolve merge conflict and fix bedrock thinking test flakiness by @jquinter in https://github.com/BerriAI/litellm/pull/21216
[test] Fix flaky tests caused by module reloading and missing mocks by @jquinter in https://github.com/BerriAI/litellm/pull/19747
Fix SSO test flakiness by correctly mocking premium_user by @jquinter in https://github.com/BerriAI/litellm/pull/21227
fix: make policy_resolve_endpoints importable without FastAPI by @jquinter in https://github.com/BerriAI/litellm/pull/21075
fix(test): improve Langfuse test isolation to prevent flaky failures by @jquinter in https://github.com/BerriAI/litellm/pull/21248
fix(test): add mock isolation for test_video_content_handler_uses_get_for_openai by @jquinter in https://github.com/BerriAI/litellm/pull/21251
fix(test): add cleanup for disable_aiohttp_transport in test_extra_body_with_fallback by @jquinter in https://github.com/BerriAI/litellm/pull/21250
refactor: remove dead code from Langfuse test cleanup by @jquinter in https://github.com/BerriAI/litellm/pull/21253
fix(test): restore Langfuse client counter in test cleanup by @jquinter in https://github.com/BerriAI/litellm/pull/21254
refactor(test): remove redundant cache flush from test_openai_env_base by @jquinter in https://github.com/BerriAI/litellm/pull/21257
fix(test): add environment cleanup for Vertex AI rerank tests by @jquinter in https://github.com/BerriAI/litellm/pull/21268
fix(test): update reasoning_effort test to expect dict format by @jquinter in https://github.com/BerriAI/litellm/pull/21271
fix(test): add environment cleanup for Vertex AI GPT-OSS tests by @jquinter in https://github.com/BerriAI/litellm/pull/21272
fix(test): add environment cleanup for Vertex AI Qwen tests by @jquinter in https://github.com/BerriAI/litellm/pull/21273
fix(test): use async side_effect for client.post mock in watsonx test by @jquinter in https://github.com/BerriAI/litellm/pull/21275
fix(test): mock vertexai module in GPT-OSS tests to prevent authentication by @jquinter in https://github.com/BerriAI/litellm/pull/21276
fix(test): update test_other_constraints_preserved for new schema filtering by @jquinter in https://github.com/BerriAI/litellm/pull/21217
fix(deps): add fakeredis for pod lock manager tests by @jquinter in https://github.com/BerriAI/litellm/pull/21281
fix(test): clear tokenizer LRU cache for test isolation by @jquinter in https://github.com/BerriAI/litellm/pull/21279
fix(test): mock environment variables for callback validation test by @jquinter in https://github.com/BerriAI/litellm/pull/21286
Fix/21193 chatgpt codex unsupported params by @jayy-77 in https://github.com/BerriAI/litellm/pull/21209
Add routing based on if reasoning is supported or not by @Sameerlite in https://github.com/BerriAI/litellm/pull/21302
Fix converse anthropic usage object according to v1/messages specs by @Sameerlite in https://github.com/BerriAI/litellm/pull/21295
Managed batches - Misc bug fixes by @ephrimstanley in https://github.com/BerriAI/litellm/pull/21157
fix(bedrock): clamp thinking.budget_tokens to minimum 1024 by @mjkam in https://github.com/BerriAI/litellm/pull/21306
Add doc for OpenAI Agents SDK with LiteLLM by @Sameerlite in https://github.com/BerriAI/litellm/pull/21311
Litellm oss staging 02 14 20262 by @Sameerlite in https://github.com/BerriAI/litellm/pull/21307
fix: virutal key grace period from env/UI by @Harshit28j in https://github.com/BerriAI/litellm/pull/20321
fix: SSO PKCE support fails in multi-pod Kubernetes deployments by @Harshit28j in https://github.com/BerriAI/litellm/pull/20314
fix(deps): add pytest-postgresql for db schema migration tests by @jquinter in https://github.com/BerriAI/litellm/pull/21280
fix(test): replace caplog with custom handler for parallel execution by @jquinter in https://github.com/BerriAI/litellm/pull/21282
fix(test): correct async mock for video generation logging test by @jquinter in https://github.com/BerriAI/litellm/pull/21283
fix(test): add cleanup fixture and no_parallel mark for MCP tests by @jquinter in https://github.com/BerriAI/litellm/pull/21284
Litellm anthropic doc beta header by @Sameerlite in https://github.com/BerriAI/litellm/pull/21320
Fix: Exclude tool params for models without function calling support (#21125) by @AtharvaJaiswal005 in https://github.com/BerriAI/litellm/pull/21244
fix(proxy): handle missing DATABASE_URL in append_query_params by @vincentkoc in https://github.com/BerriAI/litellm/pull/21239
fix(mcp): revert StreamableHTTPSessionManager to stateless mode by @michelligabriele in https://github.com/BerriAI/litellm/pull/21323
UI - Content Filters, help edit/view categories and 1-click add categories + go to next page by @krrishdholakia in https://github.com/BerriAI/litellm/pull/21223
Fix OCI Grok output pricing by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/21329
[Infra] Bumping proxy extras version by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21332
[Infra] Bumping proxy extras for release branch by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/21333
docs: add Semgrep & OOM fixes section to v1.81.12 release notes by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/21334

New Contributors

@mjkam made their first contribution in https://github.com/BerriAI/litellm/pull/21306
@AtharvaJaiswal005 made their first contribution in https://github.com/BerriAI/litellm/pull/21244
@vincentkoc made their first contribution in https://github.com/BerriAI/litellm/pull/21239

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.81.12-nightly...v1.81.13

Open source →

1.81.97 Feb 2026Deprecated

fix(test): update deprecated gemini embedding model by @shin-bot-litellm in https://github.com/BerriAI/litellm/pull/20621

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-stable

Open source →

litellm

Release timeline

Releases

What's Changed

New Contributors

What's Changed

New Contributors

What's Changed

What's Changed

New Contributors

What's Changed

New Contributors

What's Changed

New Contributors