LiteLLM

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.

This release adds extensive model support, new UI and agent gateway features, and numerous bug fixes and performance improvements across routing, authentication, and API handling.

Release v1.80.9.dev5 contains no listed changes; refer to the full changelog for details.

This release adds Helicone and SAP Gen AI providers, a new NVIDIA model, and a dynamic rate limiter with TTL support, along with documentation and minor routing updates.

This release adds several new features such as cache polling, Bedrock OSS models, Sumologic webhook integration, and new provider support, while also fixing numerous bugs including Docker directory handling, Anthropic streaming issues, and response API errors.

This release adds a User Info Delete modal and spend logging enhancements, and includes several UI and backend bug fixes.

This release adds extensive new features—including Guardrail API enhancements, OTEL integration, new model support, and UI improvements—while delivering numerous bug fixes and minor deprecations.

This release adds extensive new features such as Guardrail API tool‑call checks, OTEL integration, new model support, and enhanced UI capabilities, while also delivering numerous bug fixes and minor deprecations.

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

This release adds extensive new features—including Guardrail tool‑call checks, OTEL integration, new model support, and UI enhancements—while fixing numerous bugs and introducing a breaking change that renames `output_tokens_details` to `completion_tokens_details`.

This release focuses heavily on UI improvements, infrastructure updates, and expanding provider support, including new features for guardrails and cost tracking. A key change is the deprecation of the legacy `/spend/logs` endpoint in favor of `/spend/logs/v2`.

This release introduces a rebuilt UI, numerous new providers and model support, extensive guardrail enhancements, and many bug fixes, while deprecating the old `spend/logs` endpoint and removing feature flags.

This release focuses heavily on UI improvements, infrastructure updates, and expanding provider support, including new features for guardrails and cost tracking. Key updates include the addition of publicai.co and Z.AI providers, and deprecation of the old spend/logs endpoint.

This release adds guardrail support for pass‑through endpoints, a new publicai.co provider, UI enhancements, and several bug fixes, while upgrading websockets to version 15.

This release introduces numerous new features such as organization usage UI, WatsonX audio transcription, Vertex RAG support, and several API enhancements, along with bug fixes and a version bump to 0.4.9.

This release focuses heavily on stability, bug fixes across various providers (Vertex AI, OCI, Bedrock), and significant feature additions, including support for Claude Opus 4.5 and enhanced UI capabilities for permission and OAuth2 management. Several UI noise reductions and fixes for streaming/logging were also implemented.

This release adds Azure GPT‑5.1 and Vertex AI Image Edit support, introduces MCP Hub and UI model comparison, and includes several bug fixes and security improvements.

This release focuses heavily on bug fixes across various providers (Vertex AI, OCI, Azure, Bedrock) and significant UI/UX improvements, alongside adding support for new models like Claude Opus 4.5 and new features like OAuth2 registration and tool permission guardrails.

This release focuses heavily on stability, fixing numerous bugs across various providers (Vertex AI, OCI, Azure, Gemini) and enhancing permission management and UI consistency. New features include support for Claude Opus 4.5, Claude Skills API, and expanded OAuth2/tool permission configurations.

No specific changes were listed in the release notes; the release appears to contain no documented breaking changes, new features, deprecations, or bug fixes.

This release fixes UI noise by reverting to console outputs.

This release adds numerous new models and UI features, upgrades pydantic to 2.11.0, and includes a large set of bug fixes and performance improvements.

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

The release adds several UI enhancements, expands Prompt Management capabilities, updates cost maps, and introduces support for new models, while fixing numerous bugs and a breaking change that makes gpt-5 models default to response mode.

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

Patch release with no documented changes.

This release adds /delete support for files and /cancel support for batches, updates SSO documentation, and fixes AI Gateway JWT auth handling for Team Tags.

No changes were listed in the release notes; the update only references the full changelog.

Release notes contain only a link to the full changelog; no specific changes are listed.

This release introduces significant UI enhancements, new model support (including Day 0 Gemini and Deepseek), and crucial backend refactoring for the MCP client lifecycle. It also includes various bug fixes across providers and UI components.

The release notes only provide a link to the full changelog and do not list specific changes.

This release introduces support for the new gpt-5.1 family models and adds significant features to the UI, Model Management API, and various provider integrations like RunwayML and fal-ai. It also removes generic exception handling, improving error visibility.

The release notes only reference the full changelog link and do not list specific changes.

The release notes only reference a link to the full changelog and do not list specific changes.

This release adds several new features such as RunwayML image generation, expanded Gemini image support, and bearer token auth for Bedrock AgentCore, while also fixing a range of UI and authentication bugs.

This release adds several UI enhancements, new provider support, and numerous bug fixes, including a Zscaler AI Guard hook and RunwayML video generation provider.

This release updates the CI/CD Docker version for end-to-end UI tests and introduces a new Zscaler AI Guard hook.

This release adds several UI enhancements, new provider and routing features, and numerous bug fixes across management endpoints, streaming, and budget handling.

This release adds Vertex and Gemini Videos APIs with cost tracking, Azure Content Policy error support, and gpt-4o-transcribe cost tracking, along with several UI and Prisma runtime fixes.

Litellm v1.79.3-nightly adds Vertex and Gemini Videos APIs with cost tracking, Azure Content Policy error support, and gpt-4o-transcribe cost tracking, while delivering several bug fixes and documentation updates.

This release introduces significant feature enhancements across vector stores (Milvus, Azure AI), OCR providers (VertexAI, Azure AI Doc Intelligence), and new integrations like Bedrock Agentcore and CyberArk Secrets Manager. Numerous bug fixes address issues related to Pydantic warnings, API parameter handling, and cost calculation across various providers.

This release introduces significant feature enhancements, including expanded vector store support (Milvus, Azure AI), new OCR providers (VertexAI, Azure AI Doc Intelligence), and various UI improvements. Numerous bug fixes address issues across providers like AWS Bedrock, Azure, Gemini, and Anthropic, alongside memory leak resolutions related to Pydantic warnings.

No changelog items were provided for this release; therefore there are no documented breaking changes, deprecations, new features, or bug fixes.

This release introduces significant feature enhancements, including Milvus vector store support and expanded Passthrough API capabilities for Azure AI Vector Stores. It also addresses several critical bugs related to memory usage, AWS Bedrock, and model configuration.

This release introduces significant feature enhancements, including Milvus vector store support and Azure AI Vector Store improvements, alongside numerous bug fixes across various integrations and the UI.

This release introduces significant enhancements to vector store support (Milvus, Azure AI), adds custom provider support for video endpoints, and resolves several critical bugs related to Pydantic warnings, AWS Bedrock, and Azure API handling. It also includes various UI improvements and fixes.

This release introduces significant feature enhancements, including support for Lasso API v3, OpenTelemetry context propagation, and various UI improvements. Numerous bug fixes address issues across Azure OpenAI, logging, guardrails, and provider integrations.

This release introduces significant feature enhancements, including support for Lasso API v3, OpenTelemetry context propagation, and various UI improvements for credential and guardrail management. Numerous bug fixes address issues across Azure OpenAI, logging, and provider configurations.

No specific changelog details were provided; refer to the full changelog link for information.

This release introduces significant enhancements across observability (OpenTelemetry), guardrails, and the UI, alongside numerous bug fixes for providers like Azure OpenAI and improved performance.

This release introduces several new features, including support for dynamic client registration, OpenTelemetry context propagation, and FAL AI Image Generations. Numerous bug fixes address issues across Azure OpenAI, Guardrails, logging, and UI components.

This development release primarily addresses a bug where the completion endpoint failed for Azure OpenAI when using gpt-4-turbo.

This release introduces significant feature enhancements, particularly around Search APIs, Vector Stores (Vertex AI), and Guardrail integration across various endpoints. Numerous bug fixes address issues related to error handling, configuration mapping, and security for the Responses API.

This release introduces significant feature enhancements, including support for new Search APIs (DataforSEO, Google PSE), expanded Vector Store capabilities (Vertex AI Search), and major updates to Guardrail functionality across various endpoints. Numerous bug fixes address issues related to error handling, configuration mapping, and cost tracking.

This release introduces team-level rate limit controls and enhances guardrail capabilities with content masking and streaming support for PANW Prisma AIRS. Several bug fixes address memory leaks and configuration handling.

This release focuses on stability with fixes for the Passthrough Endpoint.

This release introduces extensive support for various search APIs (Perplexity, Tavily, Parallel AI, EXA AI) and adds Guardrails support. Several bug fixes address issues related to Ollama parsing, budget enforcement, and configuration renaming.

This release focuses heavily on bug fixes across various providers, including Anthropic, OpenAI Realtime API, and Gemini, alongside introducing new Azure AVA TTS and cost tracking features.

This release introduces team-level rate limiting features and enhances guardrail capabilities with content masking and streaming support. It also includes several bug fixes addressing memory leaks and configuration handling.

This release introduces team-level rate limiting controls and enhances guardrail capabilities with content masking and streaming support. Several bug fixes address memory leaks and configuration handling in the proxy server.

This release introduces Global Cross-Region Inference for Bedrock and includes several bug fixes related to token counting, budget settings, and Bedrock/MCP integration.

This release focuses on numerous bug fixes across UI, pricing, and model integrations, including enabling streaming for GPT-OSS on Bedrock and adding new API guardrails.

This release introduces new features like global vendor discounts, UI discount settings, and support for Gemini 2.5 Flash and new models, alongside substantial performance improvements in the router and various bug fixes.

This release introduces significant feature enhancements, including GPT-5 reasoning support, new Anthropic model versions (Haiku 4.5), and expanded admin capabilities like spending reports. Several bug fixes address pricing inaccuracies and endpoint response formats.

This release introduces an update to the LiteLLM Proxy Docker image, enabling the use of STORE_MODEL_IN_DB=True directly within the containerized environment.

This release updates the Docker image tag for the LiteLLM Proxy to v1.78.0.rc.2 and promotes the Hosted Proxy Alpha service.

This release introduces support for GPT-5 reasoning content and GPT-5-Codex on Claude Code, alongside documentation updates and new Docker image availability.

This release primarily focuses on documentation updates and cleanup, including building the UI for the documentation.

This release primarily updates the stable Docker image tag for the LiteLLM Proxy to v1.77.7-stable and provides information about the hosted proxy offering. Load test results for the proxy are also included.

This release introduces support for new Azure AI, Vertex AI Gemma, and OCI Cohere models, alongside EnkryptAI Guardrails integration. Numerous bug fixes focus on session management, rate limiting, and UI stability.

This release updates the LiteLLM Proxy Docker image tag to v1.77.7.dev16 and provides information about the Hosted Proxy Alpha service.

This release updates the LiteLLM Proxy Docker image tag to v1.77.7.dev15 and promotes the Hosted Proxy Alpha service.

This release updates the Docker image tag for the LiteLLM Proxy to v1.77.7.dev14 and promotes the Hosted Proxy Alpha service.

This release updates the LiteLLM Proxy Docker image to v1.77.7.gemma2 and announces the availability of a Hosted Proxy Alpha service.

This release updates the LiteLLM Proxy Docker image tag to v1.77.7.dev13 and provides information about the Hosted Proxy Alpha offering.

This release focuses on stability and feature enhancements, including fixes for costing, rate limiting, and Anthropic tool calls, alongside the addition of EnkryptAI Guardrails.

This release updates the LiteLLM Proxy Docker image tag to v1.77.7.dev12 and announces the availability of a Hosted Proxy Alpha program.

This release focuses on stability and security by fixing costing issues, improving Anthropic adapter reliability, and enhancing credential redaction. It also introduces support for EnkryptAI Guardrails and new Azure AI models.