LiteLLM

This release focuses on bug fixes, specifically removing a duplicate schema definition and introducing spend logging within the Release Candidate build.

LiteLLM v1.81.6.rc.4 focuses on stability by fixing several bugs related to parameter passing (like max_tokens for Azure) and response streaming across various providers.

This patch release backports a stateless fix for StreamableHTTPSessionManager to the v1.81.12-stable branch.

This release appears to be a maintenance or internal version bump, indicated by the comparison range v1.81.12-stable to v1.81.12-stable_gpt-5.3, with no detailed changes provided in the snippet.

This release provides an update to the nightly build, linking to the full comparison between the previous development version and the new nightly version.

This release focuses primarily on bug fixes across various integrations, including recovery from zombie processes, improved pricing application, and fixes related to rate limiting and authentication flows. Several recent fixes were also reverted.

This release addresses a critical CVE by fixing issues related to the identification and handling of the 'presidio' model integration.

This release primarily contains internal updates and links to the full comparison view for detailed changes.

This release introduces new features like custom favicon support, configurable semantic cache dimensions, and guardrail policy versioning. Numerous bug fixes address issues across Bedrock, budget configuration, testing stability, and model cost mapping.

This release introduces new model pricing, enhanced content filtering with topic blockers, and a new guardrail hook for voice transcription, alongside a fix for Replicate server communication.

This release introduces several new features, including custom favicon support, configurable semantic cache dimensions, and new guardrail policies. Numerous bug fixes address issues across Bedrock integration, budget calculation, testing stability, and data normalization.

This release introduces new features like custom proxy favicons, configurable semantic cache dimensions, and guardrail policy versioning. Numerous bug fixes address issues across Bedrock integration, budget tracking, testing stability, and data normalization.

This release introduces new features like custom favicon support for the proxy, configurable semantic cache dimensions, and guardrail monitoring. It also includes numerous bug fixes across providers like Bedrock and Anthropic, and utility improvements like parameter key normalization.

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.

This release introduces support for Gemini 3.1 Pro Preview, adds various policy template features, and includes extensive bug fixes across proxying, CI/CD workflows, and model parameter handling. Several tests requiring external services were skipped to improve CI stability.

This release focuses heavily on UI enhancements, introducing new guardrail features, performance optimizations across streaming and cost calculation, and significant stability fixes for proxy connections and testing infrastructure.

LiteLLM v1.81.12-stable focuses on stability by fixing several bugs related to parameter passing, streaming responses, and context length validation across various providers.

This release introduces a new Prompt Management API, adds support for several new models and compliance features like EU AI Act templates, and includes numerous performance improvements and bug fixes across routing, proxy, and testing infrastructure.

This release introduces a new Prompt Management API and significant UI enhancements, including Access Group selection and Usage filtering. It also contains extensive bug fixes focused heavily on improving test stability and isolation across various integrations.

This release focuses heavily on improving test stability across various integrations (Langfuse, Vertex AI, SSO) and introduces UI enhancements for Access Groups. It also includes fixes for parameter handling in chat models and updates to managed batch functionality.

This patch release corrects the model name mapping for Gemini 1.5 Flash to use the correct preview identifier.

This patch release fixes a bug where Gemini 1.5 Pro incorrectly errored when the response_format parameter was used.

This release appears to be a patch update (v1.81.9-stable.patch.1) following a nightly build, with details available via the provided comparison link.

This release introduces new features like IBM watsonx.ai rerank support, Bedrock structured output API, and performance improvements in routing logic. Numerous bug fixes address issues across proxy headers, metrics counting, model parameter handling, and CI/testing stability.

This patch release addresses a critical bug where streaming responses for Gemini 1.5 Pro were failing, ensuring correct behavior when streaming is enabled.

This release introduces OAuth flow support for Azure OpenAI, configurable via environment variables.

This release introduces a new Prompt Management API and significant UI enhancements, including access group selectors and usage filtering. It also includes extensive bug fixes focused heavily on improving test stability and isolation across various providers and features.

This release appears to be a development build focused on OAuth integration, as indicated by the version tag 1.81.3-stable.dev.oauth.

This release primarily consists of internal updates and bug fixes, with the full details available in the comparison link.

This release introduces support for extracting metadata specifically for the Gemini 1.5 Pro model.

This release primarily addresses a bug in the Anthropic provider related to incorrect model name setting for Sonnet, ensuring proper model identification.

This release focuses heavily on infrastructure improvements, particularly stabilizing tests across multiple providers and fixing various bugs related to API parameters, SSO, and managed batches. New UI features include Access Group selection and Content Filter management.

This release focuses heavily on improving test stability across various integrations (Langfuse, Vertex AI, SSO) and fixing numerous minor bugs. New features include UI enhancements for Access Groups and Content Filters, alongside updates to reasoning handling and model parameter exclusions.

This release primarily contains internal testing and development builds, indicated by the version tag v1.81.10.dev1.

This release contains the changelog from v1.81.12-nightly to v1.81.12.rc.1, detailed in the provided comparison link.

This release focuses heavily on bug fixes across various providers (Azure, OCI, Anthropic, Vertex AI) and internal systems like the scheduler and proxy. It also introduces several new features, including enhanced Guardrails, new model support (MiniMax, Vertex GLM-5), and UI improvements for MCP management and Zscaler AI Guard.

This release focuses heavily on bug fixes across various providers (including Anthropic, Vertex AI, and GigaChat) and significant enhancements to the UI, including new budget management features and improved admin panels. It also introduces support for new models like Qwen3-235B and Claude Opus 4.6.

This release primarily serves as a development test build, linking to the full comparison changelog for details.

This release primarily links to the full changelog for version v0.1, indicating a minor version update or specific build tag promotion.

This release introduces new configuration options, enhanced guardrail capabilities, and support for new models like MiniMax. Numerous bug fixes address issues related to streaming errors, queue management, Azure compatibility, and model metadata synchronization.

This patch release focuses on stability, fixing streaming issues with Azure OpenAI and correcting token usage calculation for Gemini 1.5 Flash.

This release focuses heavily on stability, security fixes (including CVEs), and extensive UI/UX improvements across logging, teams, and authentication flows. New features include support for Websearch interception hooks and expanded model support for Anthropic, Sarvam AI, and Perplexity.

This patch release fixes a bug where streaming requests failed for the Anthropic Claude 3 Opus model via the completion endpoint.

This release focuses heavily on stability, bug fixes across various providers (including Bedrock, Cohere, Vertex AI), and significant improvements to the LiteLLM UI and OAuth2 support. New features include Websearch interception and support for Sarvam AI and Perplexity Research API.

This release focuses heavily on stability, security fixes (including critical CVEs), and extensive UI improvements and refactoring. New features include support for Websearch interception hooks and expanded model/API support for Anthropic, Sarvam AI, and Perplexity.

This release primarily serves as a stable tag for version v1.81.3, referencing the changes made since the previous development build.

This release focuses heavily on bug fixes across various providers (including Anthropic, Vertex AI, and GigaChat) and significant enhancements to the UI, including new budget management features and model cost map updates. Key improvements were made to tracing, caching performance, and general stability.

This release focuses heavily on bug fixes across various providers (including Vertex AI, GigaChat, and Anthropic), significant UI enhancements for administration and usage tracking, and expanded model support, notably for Claude Opus 4.6 and new OpenRouter/ElevenLabs models.

This hotfix release addresses a specific user_id issue found in the /key/list endpoint.

This patch release addresses critical bugs related to the Gemini 1.5 Flash model, specifically fixing incorrect empty tool_calls responses and 400 errors when using tool_code.

This release primarily contains a link to the full changelog comparing versions v1.81.0-stable and v1.80.0-stable.opus-4-6.

This release focuses on UI enhancements, adding new models via OpenRouter, and fixing several internal regressions and inconsistencies, particularly around provider responses and typing.

This release focuses on bug fixes for the Ollama provider, specifically addressing issues with empty choices and incorrect finish reasons in the completion endpoint.

Release v1.81.3.rc.6 primarily focuses on bug fixes, addressing incorrect parameter passing for Azure OpenAI and improving streaming response handling across providers.

This release focuses heavily on bug fixes across various providers like Gemini, Vertex AI, and AWS Bedrock, alongside significant feature additions to the UI, Search API, and LiteLLM Vector Stores, including new model support.

This release focuses heavily on bug fixes across various providers (Gemini, AWS, Azure, Anthropic) and significant enhancements to the UI, including new usage reporting features and improved search capabilities. New models and integrations, such as the Claude Agent SDK, were also added.

This release focuses heavily on bug fixes across various providers like Gemini, AWS Bedrock, and Vertex AI, alongside significant feature additions to the UI, Search API, and LiteLLM Vector Stores, including new model support.

This patch release focuses on stability improvements, primarily fixing issues related to API key handling and token reporting for the Azure OpenAI provider, along with resolving streaming response truncation bugs.

This release appears to be a development build (v1.81.3.dev1) following a release candidate (v1.81.3.rc.4), with the full changelog available via the provided comparison link.

This release focuses on stability, introducing features like Bedrock converse caching and configurable CLI JWT expiration, alongside numerous bug fixes and infrastructure improvements to stabilize testing.

This release introduces significant enhancements to observability (Datadog, Prometheus metrics), adds support for Vercel AI Gateway embeddings, and includes numerous bug fixes across model integrations and UI functionality.

This release contains patch updates for LiteLLM, detailed in the full changelog link.

This release primarily consists of internal updates and bug fixes, as indicated by the comparison between release candidates v1.81.3.rc.3 and v1.81.3.rc.4.

This release primarily contains internal updates and bug fixes, detailed in the linked comparison view.

This release (v1.81.3.rc.2) is a release candidate update, with the full changelog available via the provided comparison link.

This release primarily points to the full changelog for version v1.81.3.rc.1, indicating minor updates or release candidate finalization.

This release primarily serves as a nightly update, linking to the full comparison between v1.81.3.rc and v1.81.3-nightly.

This release focuses heavily on bug fixes across various providers (Bedrock, Ollama, Google) and infrastructure components like logging and routing. Key features include support for Azure OpenAI v1 API, enhanced retry mechanisms, and updates to Gemini and Volcengine integrations.

This release marks the stable release of version 1.81.0, following the release candidate 5.

This release primarily consists of minor updates and bug fixes, detailed in the full changelog comparing versions v1.81.0.rc.4 and v1.81.0.rc.5.

This release contains the full changelog available via the provided comparison link between v1.81.0-nightly and v1.81.0.rc.4.

This release focuses heavily on bug fixes across various providers (Bedrock, Ollama, Groq, Gemini) and internal systems like logging and routing. New features include enhanced retry logic for completions and support for Azure OpenAI v1 API and KEDA in Helm charts.

This release focuses heavily on UI improvements, including new status queries and views for deleted resources, alongside adding Websearch support for Claude Code and fixing reliability issues like OOMs.

This release focuses heavily on UI enhancements, including new status queries and views for deleted resources, alongside adding Websearch support for Claude Code and fixing reliability issues with image handling.

This release incorporates a merge from a pull request initiated by dominicfeliton and merged by yuneng-jiang.

This release primarily focuses on bug fixes, including ensuring correct parameter passing for Azure OpenAI and improving streaming response handling.

This release focuses on UI enhancements for team management, infrastructure updates including schema migrations for keys and teams, and several bug fixes across Vertex AI integration and logging. Several recent changes were also reverted to maintain stability.

This release introduces new model pricing, enhances guardrail functionality with a default failopen option, and includes numerous fixes across model integrations, pricing accuracy, and UI components. Performance bottlenecks under heavy load were also addressed.

This hotfix release addresses a critical issue related to Azure Storage circular references.

This release focuses heavily on bug fixes across various providers (Gemini, Anthropic, OCI) and internal systems like guardrails and pricing. It also introduces several UI enhancements and infrastructure updates, including Helm chart versioning sync.

This release focuses heavily on bug fixes across various providers like Gemini, Anthropic, and OCI, alongside adding new features such as Bedrock service tier translation and support for replicate chat models. It also includes documentation updates regarding load balancing and Redis requirements.

This release contains the changelog link for version v1.80.15.rc.2 compared to the previous nightly build.

This release introduces several new provider integrations, enhanced Prometheus metrics for monitoring, and numerous bug fixes across proxying, routing, and provider configurations. Performance improvements were also made to provider configuration lookups.

This release introduces numerous new features, including provider additions (abliteration.ai, Bedrock for token counting), enhanced Prometheus metrics, and UI improvements for the Playground. Numerous bug fixes address issues across proxy streaming, provider configurations (Gemini, Azure), security, and internal workflows.

This release introduces significant new features like Guardrails Load Balancing, Unified Skills API, and a new Rag Search API. It also includes numerous bug fixes across pricing, integrations (like Langfuse and Datadog), and UI elements, alongside performance improvements via lazy loading.

This release introduces significant feature enhancements, including support for image tokens, AWS Polly TTS, Minimax integration, and major UI improvements like error code filtering and key management updates. It also includes substantial internal refactoring to lazy load configuration classes for better performance.

No changelog details were provided for this patch release.

This release adds several new capabilities such as Guardrails load‑balancing, a unified Skills API, Rag Search and Query APIs with rerankers, and expanded model support, while also delivering numerous bug fixes and performance improvements across CI/CD, UI, and observability components.

This release adds numerous new features such as Guardrails load balancing, a unified Skills API, and expanded model support, while delivering a large set of bug fixes and performance improvements across CI/CD, UI, and observability components.

This release adds extensive new features—including Gemini 3 flash preview support, Azure Sentinel logging, Guardrails enhancements, and a new LinkUp Search provider—while delivering numerous bug fixes and a breaking change that renames `extra_headers` to `additional_headers`.

No specific changes were listed in the release notes; refer to the full changelog for details.

No changelog details were provided beyond the link to the full comparison.

No changes were documented for this release.

This release adds numerous new providers and features—including Stability AI, Azure Cohere reranking, and VertexAI Agent Engine—while fixing a wide range of bugs and refactoring lazy imports for better performance.

No detailed changelog items were provided; see the full changelog link for specifics.

LiteLLM v1.80.10 introduces Azure GPT‑5.2 models, new security guardrail evidence, expanded UI features, and numerous bug fixes and documentation updates.

Litellm v1.80.10 introduces Azure GPT‑5.2 model support, new security guardrail evidence, JWT team‑id selection, OTEL latency metrics, UI enhancements, and a large set of bug fixes and documentation updates.

Release v1.80.8 stable was published; specific changes are not listed in the provided notes. See the full changelog for details.