●Change8

v1.80.5.dev2

📦 litellmView on GitHub →
✨ 14 features🐛 25 fixes⚡ 1 deprecations🔧 9 symbols

Summary

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.

✨ New Features

  • Added support for Claude Opus 4.5.
  • Added new API for Claude Skills API (Anthropic).
  • Added UI support for configuring tool permission guardrails.
  • Added backend support for OAuth2 auth_type registration via UI.
  • Added UI support for registering MCP OAuth2 auth_type.
  • Added cost tracking for Cohere embed passthrough endpoint.
  • Integrated Eleven Labs text-to-speech.
  • Added support for OpenAI compatible bedrock imported models (e.g., qwen).
  • Added support for Azure Anthropic models via chat completion.
  • Added Vertex AI image generation support for both Gemini and Imagen models.
  • Added day 0 support for Anthropic new features.
  • Added search API logging and cost tracking in LiteLLM Proxy.
  • Added enforce user param functionality.
  • Added new feature for deleting a User From Team which also deletes key User Created for Team.

🐛 Bug Fixes

  • Reverted UI outputs to console outputs to reduce noise.
  • Fixed MCP tool call response logging and removed unmapped param error mid-stream in responses_bridge, allowing gpt-5 web search via responses api in .completion().
  • Fixed default sample count for Vertex AI image generation handler.
  • Reverted UI change related to Organization Usage.
  • Fixed context caching for Vertex AI when handling global location.
  • Prevented duplicate spend logs in Responses API for non-OpenAI providers.
  • Fixed pydantic validation errors during OCI Provider tool call with streaming.
  • Fixed handling of None or empty contents in Gemini token counter.
  • Fixed Azure auth format for videos.
  • Fixed Bedrock passthrough auth issue.
  • Fixed gpt-5.1 temperature support when reasoning_effort is "none" or not specified.
  • Propagated x-litellm-model-id in responses.
  • Distinguished permission errors from idempotent errors in Prisma migrations.
  • Fixed non-root Docker build.
  • Added aws_bedrock_runtime_endpoint into Credential Types.
  • Fixed image edit endpoint.
  • Fixed UI issue where Default Team Settings were hidden from Proxy Admin Viewers.
  • Fixed UI issue regarding No Default Models for Team and User Settings.
  • Fixed Gemini: skipping thinking config for image models.
  • Fixed metadata 401 error when handling audio/transcriptions.
  • Made Bedrock image generation more consistent.
  • Fixed Vertex AI CreateCachedContentRequest enum error.
  • Fixed reasoning_effort="none" not working on Azure for GPT-5.1.
  • Fixed transcription exception handling for /audio/transcriptions.
  • Fixed Bedrock Claude Opus 4.5 inference profile (currently only global).

🔧 Affected Symbols

vertex_ai/image_generation_handler.pylitellm_logging.pyresponses_bridgeproxy_server.pylitellm.completion()aws_bedrock_runtime_endpointazurebedrock/audio/transcriptions

⚡ Deprecations

  • Removed unused MCP_PROTOCOL_VERSION_HEADER_NAME constant.