v1.69.0-stable

What's Changed

• [Docs] v1.69.0-stable by @ishaan-jaff in #10731
• Litellm emails smtp fixes by @ishaan-jaff in #10730
• [Docs] Email notifs by @ishaan-jaff in #10733
• Litellm staging 05 10 2025 - openai pdf url support + sagemaker chat content length error fix by @krrishdholakia in #10724

Full Changelog: v1.69.0-nightly...v1.69.0-stable

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.69.0-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	264.33108534405653	6.12787888551344	0.0	1834	0	216.09041499999648	1326.1799069999824
Aggregated	Passed ✅	240.0	264.33108534405653	6.12787888551344	0.0	1834	0	216.09041499999648	1326.1799069999824

v1.69.0-nightly

What's Changed

• build: update model in test by @krrishdholakia in #10706
• fix: support for python 3.11- (re datetime UTC) (#10471) by @ishaan-jaff in #10701
• [FIX] Update token fields in schema.prisma to use BigInt for improved… by @husnain7766 in #10697
• [Refactor] Use pip package for enterprise/ folder by @ishaan-jaff in #10709
• [Feat] Add streaming support for using bedrock invoke models with /v1/messages by @ishaan-jaff in #10710
• Add --version flag to litellm-proxy CLI by @msabramo in #10704
• Add management client docs by @msabramo in #10703
• fix(caching_handler.py): fix embedding str caching result by @krrishdholakia in #10700
• Azure LLM: fix passing through of azure_ad_token_provider parameter by @claralp in #10694
• set correct context window length for all gemini 2.5 variants by @mollux in #10690
• Fix log table bugs (after filtering logic was added) by @NANDINI-star in #10712
• fix(router.py): write file to all deployments by @krrishdholakia in #10708
• Litellm Unified File ID output file id support by @krrishdholakia in #10713
• complete unified batch id support - replace model in jsonl to be deployment model name by @krrishdholakia in #10719
• [UI] Bug Fix - Allow Copying Request / Response on Logs Page by @ishaan-jaff in #10720
• [UI] QA Logs page - Fix bug where log did not remain in focus + text overflow on error logs by @ishaan-jaff in #10725
• Add target model name validation by @krrishdholakia in #10722
• [Bug fix] - allow using credentials for /moderations by @ishaan-jaff in #10723
• [DB] Add index for session_id on LiteLLM_SpendLogs by @ishaan-jaff in #10727
• [QA Bug fix] fix: ensure model info does not get overwritten when editing a model on UI by @ishaan-jaff in #10726
• Mutable default arguments on embeddings/completion headers parameters breaks watsonx by @terylt in #10728

New Contributors

• @husnain7766 made their first contribution in #10697
• @claralp made their first contribution in #10694
• @mollux made their first contribution in #10690
• @terylt made their first contribution in #10728

Full Changelog: v1.68.2-nightly...v1.69.0-nightly

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.69.0-nightly

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 ✅	250.0	292.69430995024163	6.184694862389694	0.0	1849	0	216.9113210000262	60025.948276999996
Aggregated	Passed ✅	250.0	292.69430995024163	6.184694862389694	0.0	1849	0	216.9113210000262	60025.948276999996

v1.68.2.dev6

What's Changed

• build: update model in test by @krrishdholakia in #10706
• fix: support for python 3.11- (re datetime UTC) (#10471) by @ishaan-jaff in #10701
• [FIX] Update token fields in schema.prisma to use BigInt for improved… by @husnain7766 in #10697

New Contributors

• @husnain7766 made their first contribution in #10697

Full Changelog: v1.68.2-nightly...v1.68.2.dev6

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.2.dev6

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 ✅	190.0	210.63173736431506	6.257034907859717	0.0	1872	0	166.34112399992773	1685.74146200001
Aggregated	Passed ✅	190.0	210.63173736431506	6.257034907859717	0.0	1872	0	166.34112399992773	1685.74146200001

v1.68.2-nightly

What's Changed

• [Refactor - Filtering Spend Logs] Add status to root of SpendLogs table by @ishaan-jaff in #10661
• Filter logs on status and model by @NANDINI-star in #10670
• [Refactor] Anthropic /v1/messages endpoint - Refactor to use base llm http handler and transformations by @ishaan-jaff in #10677
• [Feat] Add support for using Bedrock Invoke models in /v1/messages format by @ishaan-jaff in #10681
• fix(factory.py): Handle system only message to anthropic by @krrishdholakia in #10678
• Realtime API - Set 'headers' in scope for websocket auth requests + reliability fix infinite loop when model_name not found for realtime models by @krrishdholakia in #10679
• Extract 'thinking' from nova response + Add 'drop_params' support for gpt-image-1 by @krrishdholakia in #10680
• New azure models by @emerzon in #9956
• Add GPTLocalhost to "docs/my-website/docs/projects" by @GPTLocalhost in #10687
• Add nscale support for streaming by @tomukmatthews in #10698

New Contributors

• @GPTLocalhost made their first contribution in #10687

Full Changelog: v1.68.1.dev4...v1.68.2-nightly

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.2-nightly

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 ✅	190.0	223.07673508503882	6.209370359620187	0.0033419646714855688	1858	1	75.31227999999146	4978.849046000022
Aggregated	Passed ✅	190.0	223.07673508503882	6.209370359620187	0.0033419646714855688	1858	1	75.31227999999146	4978.849046000022

v1.68.1.dev4

What's Changed

• Contributor PR - Return 404 when delete_verification_tokens (POST /key/delete) fai… by @ishaan-jaff in #10605
• Fix otel - follow genai semantic conventions + support 'instructions' param for tts by @krrishdholakia in #10608
• make openai model O series conditional accept provider/model by @aholmberg in #10591
• add gemini-2.5-pro-preview-05-06 model prices and context window by @marty-sullivan in #10597
• Fix: Ollama integration KeyError when using JSON response format by @aravindkarnam in #10611
• [Feat] V2 Emails - Fixes for sending emails when creating keys + Resend API support by @ishaan-jaff in #10602
• [Feat] Add User invitation emails when inviting users to litellm by @ishaan-jaff in #10615
• [Fix] SCIM - Creating SCIM tokens on Admin UI by @ishaan-jaff in #10628
• Filter on logs table by @NANDINI-star in #10644
• [Feat] Bedrock Guardrails - Add support for PII Masking with bedrock guardrails by @ishaan-jaff in #10642
• [Feat] Add endpoints to manage email settings by @ishaan-jaff in #10646
• Contributor PR - MCP Server DB Schema (#10634) by @ishaan-jaff in #10641
• Ollama - fix custom price cost tracking + add 'max_completion_token' support by @krrishdholakia in #10636
• fix cerebras llama-3.1-70b model_prices_and_context_window, not llama3.1-70b by @xsg22 in #10648
• Fix cache miss for gemini models with response_format by @casparhsws in #10635
• Add user management functionality to Python client library & CLI by @msabramo in #10627
• [BETA] Support unified file id (managed files) for batches by @krrishdholakia in #10650
• Fix Slack alerting not working if using a DB by @hypermoose in #10370
• Add support for Nscale (EU-Sovereign) Provider by @tomukmatthews in #10638
• Add New Perplexity Models by @keyute in #10652

New Contributors

• @aholmberg made their first contribution in #10591
• @aravindkarnam made their first contribution in #10611
• @xsg22 made their first contribution in #10648
• @casparhsws made their first contribution in #10635
• @hypermoose made their first contribution in #10370
• @tomukmatthews made their first contribution in #10638
• @keyute made their first contribution in #10652

Full Changelog: v1.68.1-nightly...v1.68.1.dev4

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.1.dev4

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 ✅	190.0	233.10816080888745	6.241336822394705	0.0	1868	0	166.93079599997418	5406.457653000075
Aggregated	Passed ✅	190.0	233.10816080888745	6.241336822394705	0.0	1868	0	166.93079599997418	5406.457653000075

v1.68.1.dev2

Full Changelog: v1.68.1.dev1...v1.68.1.dev2

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.1.dev2

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	271.34034604220733	6.1752223755996924	0.0	1848	0	206.34432800000013	5012.736279000023
Aggregated	Passed ✅	240.0	271.34034604220733	6.1752223755996924	0.0	1848	0	206.34432800000013	5012.736279000023

v1.68.1.dev1

What's Changed

• Github: Increase timeout of litellm tests by @zoltan-ongithub in #10568
• [Docs] Change llama-api link for litellm by @seyeong-han in #10556
• [Feat] v2 Custom Logger API Endpoints by @ishaan-jaff in #10575
• [Bug fix] JSON logs - Ensure only 1 log is emitted (previously duplicate json logs were getting emitted) by @ishaan-jaff in #10580
• Update gemini-2.5-pro-exp-03-25 max_tokens to 65,535 by @mkavinkumar1 in #10548
• Update instructor.md by @thomelane in #10549
• fix issue when databrick use external model, the delta could be empty… by @frankzye in #10540
• Add litellm-proxy CLI (#10478) by @ishaan-jaff in #10578

New Contributors

• @zoltan-ongithub made their first contribution in #10568
• @mkavinkumar1 made their first contribution in #10548
• @thomelane made their first contribution in #10549
• @frankzye made their first contribution in #10540

Full Changelog: v1.68.0-nightly...v1.68.1.dev1

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.1.dev1

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 ✅	210.0	244.34719839029643	6.203411663807808	0.0	1855	0	183.31073700005618	5362.244745999988
Aggregated	Passed ✅	210.0	244.34719839029643	6.203411663807808	0.0	1855	0	183.31073700005618	5362.244745999988

v1.68.1-nightly

What's Changed

• Add bedrock llama4 pricing + handle llama4 templating on bedrock invoke route by @krrishdholakia in #10582

Full Changelog: v1.68.1.dev2...v1.68.1-nightly

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.1-nightly

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 ✅	210.0	234.26202141345593	6.161378945167915	0.0	1843	0	179.4365540000058	3332.6730800000064
Aggregated	Passed ✅	210.0	234.26202141345593	6.161378945167915	0.0	1843	0	179.4365540000058	3332.6730800000064

v1.68.0-nightly

What's Changed

• [Contributor PR] Support Llama-api as an LLM provider (#10451) by @ishaan-jaff in #10538
• UI - fix(model_management_endpoints.py): allow team admin to update model info + fix request logs - handle expanding other rows when existing row selected + fix(organization_endpoints.py): enable proxy admin with 'all-proxy-model' access to create new org with specific models by @krrishdholakia in #10539
• [Bug Fix] UnicodeDecodeError: 'charmap' on Windows during litellm import by @ishaan-jaff in #10542
• fix(converse_transformation.py): handle meta llama tool call response by @krrishdholakia in #10541

Full Changelog: v1.67.6.dev1...v1.68.0-nightly

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.0-nightly

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

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.68.0-nightly

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 ✅	180.0	210.99923315604772	6.1894793990457675	0.0	1852	0	166.69672900002297	3755.0343799999837
Aggregated	Passed ✅	180.0	210.99923315604772	6.1894793990457675	0.0	1852	0	166.69672900002297	3755.0343799999837

v1.68.0-stable

What's Changed

• Handle more gemini tool calling edge cases + support bedrock 'stable-image-core' by @krrishdholakia in #10351
• [Feat] Add logging callback support for /moderations API by @ishaan-jaff in #10390
• [Reliability fix] Redis transaction buffer - ensure all redis queues are periodically flushed by @ishaan-jaff in #10393
• [Bug Fix] Responses API - fix for handling multiturn responses API sessions by @ishaan-jaff in #10415
• build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic in /docs/my-website by @dependabot in #10419
• docs: Fix link formatting in GitHub PR template by @user202729 in #10417
• docs: Improve documentation of phoenix logging by @user202729 in #10416
• [Feat Security] - Allow blocking web crawlers by @ishaan-jaff in #10420
• [Feat] Add support for using Bedrock Knowledge Bases with LiteLLM /chat/completions requests by @ishaan-jaff in #10413
• Revert "build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic in /docs/my-website" by @ishaan-jaff in #10421
• fix google studio url by @nonZero in #10095
• [New model] Add openai/computer-use-preview cost tracking / pricing by @ishaan-jaff in #10422
• fix(langsmith.py): respect langsmith batch size param by @krrishdholakia in #10411
• Support x-litellm-api-key header param + allow key at max budget to call non-llm api endpoints by @krrishdholakia in #10392
• Update fireworks ai pricing by @krrishdholakia in #10425
• Schedule budget resets at expectable times (#10331) by @krrishdholakia in #10333
• Embedding caching fixes - handle str -> list cache, set usage tokens for cache hits, combine usage tokens on partial cache hits by @krrishdholakia in #10424
• Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (#9995) by @ishaan-jaff in #10423
• New feature: Add Python client library for LiteLLM Proxy by @msabramo in #10445
• Add key-level multi-instance tpm/rpm/max parallel request limiting by @krrishdholakia in #10458
• [UI] Allow adding triton models on LiteLLM UI by @ishaan-jaff in #10456
• [Feat] Vector Stores/KnowledgeBases - Allow defining Vector Store Configs by @ishaan-jaff in #10448
• Add low-level interface to client library for doing HTTP requests by @msabramo in #10452
• Correctly re-raise 504 errors and Add gpt-4o-mini-tts support by @krrishdholakia in #10462
• UI - Fix filtering on key alias + support global sorting on keys by @krrishdholakia in #10455
• [Bug Fix] Ensure Non-Admin virtual keys can access /mcp routes by @ishaan-jaff in #10473
• [Fixes] Azure OpenAI OIDC - allow using litellm defined params for OIDC Auth by @ishaan-jaff in #10394
• Add supports_pdf_input: true to Claude 3.7 bedrock models by @RupertoM in #9917
• Add llamafile as a provider (#10203) by @peteski22 , in #10482
• Fix mcp.md in documentation by @1995parham in #10493
• docs(realtime): yaml config example for realtime model by @kmontocam in #10489
• Fix return finish_reason = "tool_calls" for gemini tool calling by @krrishdholakia in #10485
• Add user + team based multi-instance rate limiting by @krrishdholakia in #10497
• mypy tweaks by @msabramo in #10490
• Add vertex ai meta llama 4 support + handle tool call result in content for vertex ai by @krrishdholakia in #10492
• Fix and rewrite of token_counter by @happyherp in #10409
• [Fix + Refactor] Trigger Soft Budget Webhooks When Key Crosses Threshold by @ishaan-jaff in #10491
• [Bug Fix] Ensure Web Search / File Search cost are only added when the response includes the too call by @ishaan-jaff in #10476
• Fixes for test_team_budget_metrics and test_generate_and_update_key by @S1LV3RJ1NX in #10500
• [Feat] KnowledgeBase/Vector Store - Log StandardLoggingVectorStoreRequest for requests made when a vector store is used by @ishaan-jaff in #10509
• Don't depend on uvloop on windows (#10060) by @ishaan-jaff in #10483
• fix: PydanticDeprecatedSince20: Support for class-based config is eprecated, use ConfigDict instead. Deprecated in Pydantic V2.0 to be removed in V3.0. by @Elijas in #9372
• [Feat] Show Vector Store / KB Request on LiteLLM Logs Page by @ishaan-jaff in #10514
• Fix pytest event loop warning (#9641) by @msabramo in #10512
• UI - fix adding vertex models with reusable credentials + fix pagination on keys table + fix showing org budgets on table by @krrishdholakia in #10528
• Playwright test for team admin (#10366) by @krrishdholakia in #10470
• [QA] Bedrock Vector Stores Integration - Allow using with registry + in OpenAI API spec with tools by @ishaan-jaff in #10516
• UI - allow reassigning team to other org by @krrishdholakia in #10527
• [Models/ LLM Credentials] Fix edit credentials modal by @NANDINI-star in #10519

New Contributors

• @peteski22 made their first contribution in in #10482
• @user202729 made their first contribution in #10417
• @nonZero made their first contribution in #10095
• @RupertoM made their first contribution in #9917
• @1995parham made their first contribution in #10493
• @kmontocam made their first contribution in #10489
• @happyherp made their first contribution in #10409
• @Elijas made their first contribution in #9372

Full Changelog: v1.67.4-stable...v1.67.7-stable