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