From d45dfa899be48f0f3d6c41fcda3604951a13d6e0 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Sat, 11 Oct 2025 12:12:41 -0700 Subject: [PATCH] [Docs] v1.78.0-stable (#15452) * docs fix * docs fix --- .../release_notes/v1.77.7-stable/index.md | 2 +- .../release_notes/v1.78.0-stable/index.md | 326 ++++++++++++++++++ 2 files changed, 327 insertions(+), 1 deletion(-) create mode 100644 docs/my-website/release_notes/v1.78.0-stable/index.md diff --git a/docs/my-website/release_notes/v1.77.7-stable/index.md b/docs/my-website/release_notes/v1.77.7-stable/index.md index b5e53846b71..2a6d7788d85 100644 --- a/docs/my-website/release_notes/v1.77.7-stable/index.md +++ b/docs/my-website/release_notes/v1.77.7-stable/index.md @@ -15,7 +15,7 @@ authors: title: Backend Performance Engineer url: https://www.linkedin.com/in/alexsander-baptista/ image_url: https://media.licdn.com/dms/image/v2/D5603AQGXnziu4kqNCQ/profile-displayphoto-crop_800_800/B56ZkxEcuOKEAI-/0/1757464874550?e=1762387200&v=beta&t=9SNXLsWhx8OnYPAMQ9fqAr02oevDYEAL2vMYg2f9ieg - - name: Achintya Srivastava + - name: Achintya Rajan title: Fullstack Engineer url: https://www.linkedin.com/in/achintya-rajan/ image_url: https://media.licdn.com/dms/image/v2/D5603AQGdkEeyJTdljw/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1716271140869?e=1762387200&v=beta&t=9gOoLPeqR2E5z3KSX61EUj3HVZXmgo87vhVuSHeffjc diff --git a/docs/my-website/release_notes/v1.78.0-stable/index.md b/docs/my-website/release_notes/v1.78.0-stable/index.md new file mode 100644 index 00000000000..872c8f0337d --- /dev/null +++ b/docs/my-website/release_notes/v1.78.0-stable/index.md @@ -0,0 +1,326 @@ +--- +title: "v1.78.0-stable - MCP Gateway - Control Tool Access by Team/Key" +slug: "v1-78-0" +date: 2025-10-11T10:00:00 +authors: + - name: Krrish Dholakia + title: CEO, LiteLLM + url: https://www.linkedin.com/in/krish-d/ + image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg + - name: Ishaan Jaff + title: CTO, LiteLLM + url: https://www.linkedin.com/in/reffajnaahsi/ + image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg + - name: Alexsander Hamir + title: Backend Performance Engineer + url: https://www.linkedin.com/in/alexsander-baptista/ + image_url: https://media.licdn.com/dms/image/v2/D5603AQGXnziu4kqNCQ/profile-displayphoto-crop_800_800/B56ZkxEcuOKEAI-/0/1757464874550?e=1762387200&v=beta&t=9SNXLsWhx8OnYPAMQ9fqAr02oevDYEAL2vMYg2f9ieg + - name: Achintya Rajan + title: Fullstack Engineer + url: https://www.linkedin.com/in/achintya-rajan/ + image_url: https://media.licdn.com/dms/image/v2/D5603AQGdkEeyJTdljw/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1716271140869?e=1762387200&v=beta&t=9gOoLPeqR2E5z3KSX61EUj3HVZXmgo87vhVuSHeffjc + - name: Sameer Kankute + title: Backend Engineer (LLM Translation) + url: https://www.linkedin.com/in/sameer-kankute/ + image_url: https://media.licdn.com/dms/image/v2/D4D03AQHB_loQYd5gjg/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1719137160975?e=1762387200&v=beta&t=0jbuX-f4eSnDxBY3olI6meuYr-LMbObhFmFbRcKF5mY + +hide_table_of_contents: false +--- + +import Image from '@theme/IdealImage'; +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +## Deploy this version + + + + +``` showLineNumbers title="docker run litellm" +docker run \ +-e STORE_MODEL_IN_DB=True \ +-p 4000:4000 \ +ghcr.io/berriai/litellm:v1.78.0.rc.1 +``` + + + + + +``` showLineNumbers title="pip install litellm" +pip install litellm==1.78.0.rc.1 +``` + + + + +--- + +## Key Highlights + +- **MCP Gateway Enhancements** - Fine-grained tool control at team/key level, OpenAPI to MCP server conversion, and per-tool parameter allowlists +- **GPT-5 Pro & GPT-Image-1-Mini** - Day 0 support for OpenAI's GPT-5 Pro (400K context) and gpt-image-1-mini image generation +- **UI Performance Boost** - Replaces bloated key list calls with lean key aliases endpoint, Turbopack for faster development, and major UI refactors +- **EnkryptAI Guardrails** - New guardrail integration for content moderation +- **Tag-Based Budgets** - Support for setting budgets based on request tags +- **Azure AD & SSO** - Enhanced Azure AD default credentials selection and EntraID app roles support + +--- + +## New Models / Updated Models + +#### New Model Support + +| Provider | Model | Context Window | Input ($/1M tokens) | Output ($/1M tokens) | Features | +| -------- | ----- | -------------- | ------------------- | -------------------- | -------- | +| OpenAI | `gpt-5-pro` | 400K | $15.00 | $120.00 | Responses API, reasoning, vision, function calling, prompt caching, web search | +| OpenAI | `gpt-5-pro-2025-10-06` | 400K | $15.00 | $120.00 | Responses API, reasoning, vision, function calling, prompt caching, web search | +| OpenAI | `gpt-image-1-mini` | - | $2.00/img | - | Image generation and editing | +| OpenAI | `gpt-realtime-mini` | 128K | $0.60 | $2.40 | Realtime audio, function calling | +| Azure AI | `azure_ai/Phi-4-mini-reasoning` | 131K | $0.08 | $0.32 | Function calling | +| Azure AI | `azure_ai/Phi-4-reasoning` | 32K | $0.125 | $0.50 | Function calling, reasoning | +| Azure AI | `azure_ai/MAI-DS-R1` | 128K | $1.35 | $5.40 | Reasoning, function calling | +| Bedrock | `au.anthropic.claude-sonnet-4-5-20250929-v1:0` | 200K | $3.30 | $16.50 | Chat, reasoning, vision, function calling, prompt caching | +| Bedrock | `global.anthropic.claude-sonnet-4-5-20250929-v1:0` | 200K | $3.00 | $15.00 | Chat, reasoning, vision, function calling, prompt caching | +| Bedrock | `global.anthropic.claude-sonnet-4-20250514-v1:0` | 1M | $3.00 | $15.00 | Chat, reasoning, vision, function calling, prompt caching | +| Bedrock | `cohere.embed-v4:0` | 128K | $0.12 | - | Embeddings, image input support | +| OCI | `oci/cohere.command-latest` | 128K | $1.56 | $1.56 | Function calling | +| OCI | `oci/cohere.command-a-03-2025` | 256K | $1.56 | $1.56 | Function calling | +| OCI | `oci/cohere.command-plus-latest` | 128K | $1.56 | $1.56 | Function calling | +| Together AI | `together_ai/moonshotai/Kimi-K2-Instruct-0905` | 262K | $1.00 | $3.00 | Function calling | +| Together AI | `together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct` | 262K | $0.15 | $1.50 | Function calling | +| Together AI | `together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking` | 262K | $0.15 | $1.50 | Function calling | +| Vertex AI | MedGemma models | Varies | Varies | Varies | Medical-focused Gemma models on custom endpoints | +| Watson X | 27 new foundation models | Varies | Varies | Varies | Granite, Llama, Mistral families | + +#### Features + +- **[OpenAI](../../docs/providers/openai)** + - Add GPT-5 Pro model configuration and documentation - [PR #15258](https://github.com/BerriAI/litellm/pull/15258) + - Add stop parameter to non-supported params for GPT-5 - [PR #15244](https://github.com/BerriAI/litellm/pull/15244) + - Day 0 Support, Add gpt-image-1-mini - [PR #15259](https://github.com/BerriAI/litellm/pull/15259) + - Add gpt-realtime-mini support - [PR #15283](https://github.com/BerriAI/litellm/pull/15283) + - Add gpt-5-pro-2025-10-06 to model costs - [PR #15344](https://github.com/BerriAI/litellm/pull/15344) + - Minimal fix: gpt5 models should not go on cooldown when called with temperature!=1 - [PR #15330](https://github.com/BerriAI/litellm/pull/15330) + +- **[Snowflake Cortex](../../docs/providers/snowflake)** + - Add function calling support for Snowflake Cortex REST API - [PR #15221](https://github.com/BerriAI/litellm/pull/15221) + +- **[Gemini](../../docs/providers/gemini)** + - Fix header forwarding for Gemini/Vertex AI providers in proxy mode - [PR #15231](https://github.com/BerriAI/litellm/pull/15231) + +- **[Azure](../../docs/providers/azure)** + - Removed stop param from unsupported azure models - [PR #15229](https://github.com/BerriAI/litellm/pull/15229) + - Fix(azure/responses): remove invalid status param from azure call - [PR #15253](https://github.com/BerriAI/litellm/pull/15253) + - Add new Azure AI models with pricing details - [PR #15387](https://github.com/BerriAI/litellm/pull/15387) + - AzureAD Default credentials - select credential type based on environment - [PR #14470](https://github.com/BerriAI/litellm/pull/14470) + +- **[Bedrock](../../docs/providers/bedrock)** + - Add Global Cross-Region Inference - [PR #15210](https://github.com/BerriAI/litellm/pull/15210) + - Add Cohere Embed v4 support for AWS Bedrock - [PR #15298](https://github.com/BerriAI/litellm/pull/15298) + - Fix(bedrock): include cacheWriteInputTokens in prompt_tokens calculation - [PR #15292](https://github.com/BerriAI/litellm/pull/15292) + - Add Bedrock AU Cross-Region Inference for Claude Sonnet 4.5 - [PR #15402](https://github.com/BerriAI/litellm/pull/15402) + - Converse → /v1/messages streaming doesn't handle parallel tool calls with Claude models - [PR #15315](https://github.com/BerriAI/litellm/pull/15315) + +- **[Vertex AI](../../docs/providers/vertex)** + - Implement Context Caching for Vertex AI provider - [PR #15226](https://github.com/BerriAI/litellm/pull/15226) + - Support for Vertex AI Gemma Models on Custom Endpoints - [PR #15397](https://github.com/BerriAI/litellm/pull/15397) + - VertexAI - gemma model family support (custom endpoints) - [PR #15419](https://github.com/BerriAI/litellm/pull/15419) + - VertexAI Gemma model family streaming support + Added MedGemma - [PR #15427](https://github.com/BerriAI/litellm/pull/15427) + +- **[OCI](../../docs/providers/oci)** + - Add OCI Cohere support with tool calling and streaming capabilities - [PR #15365](https://github.com/BerriAI/litellm/pull/15365) + +- **[Watson X](../../docs/providers/watsonx)** + - Add Watson X foundation model definitions to model_prices_and_context_window.json - [PR #15219](https://github.com/BerriAI/litellm/pull/15219) + - Watsonx - Apply correct prompt templates for openai/gpt-oss model family - [PR #15341](https://github.com/BerriAI/litellm/pull/15341) + +- **[OpenRouter](../../docs/providers/openrouter)** + - Fix - (openrouter): move cache_control to content blocks for claude/gemini - [PR #15345](https://github.com/BerriAI/litellm/pull/15345) + - Fix - OpenRouter cache_control to only apply to last content block - [PR #15395](https://github.com/BerriAI/litellm/pull/15395) + +- **[Together AI](../../docs/providers/togetherai)** + - Add new together models - [PR #15383](https://github.com/BerriAI/litellm/pull/15383) + +### Bug Fixes + +- **General** + - Bug fix: gpt-5-chat-latest has incorrect max_input_tokens value - [PR #15116](https://github.com/BerriAI/litellm/pull/15116) + - Fix reasoning response ID - [PR #15265](https://github.com/BerriAI/litellm/pull/15265) + - Fix issue with parsing assistant messages - [PR #15320](https://github.com/BerriAI/litellm/pull/15320) + - Fix litellm_param based costing - [PR #15336](https://github.com/BerriAI/litellm/pull/15336) + - Fix lint errors - [PR #15406](https://github.com/BerriAI/litellm/pull/15406) + +--- + +## LLM API Endpoints + +#### Features + +- **[Responses API](../../docs/response_api)** + - Added streaming support for response api streaming image generation - [PR #15269](https://github.com/BerriAI/litellm/pull/15269) + - Add native Responses API support for litellm_proxy provider - [PR #15347](https://github.com/BerriAI/litellm/pull/15347) + - Temporarily relax ResponsesAPIResponse parsing to support custom backends (e.g., vLLM) - [PR #15362](https://github.com/BerriAI/litellm/pull/15362) + +- **[Files API](../../docs/files_api)** + - Feat(files): add @client decorator to file operations - [PR #15339](https://github.com/BerriAI/litellm/pull/15339) + +- **[/generateContent](../../docs/providers/gemini)** + - Fix gemini cli by actually streaming the response - [PR #15264](https://github.com/BerriAI/litellm/pull/15264) + +- **[Azure Passthrough](../../docs/pass_through/azure)** + - Azure - passthrough support with router models - [PR #15240](https://github.com/BerriAI/litellm/pull/15240) + +#### Bugs + +- **General** + - Fix x-litellm-cache-key header not being returned on cache hit - [PR #15348](https://github.com/BerriAI/litellm/pull/15348) + +--- + +## Management Endpoints / UI + +#### Features + +- **Proxy CLI Auth** + - Proxy CLI - dont store existing key in the URL, store it in the state param - [PR #15290](https://github.com/BerriAI/litellm/pull/15290) + +- **Models + Endpoints** + - Make PATCH `/model/{model_id}/update` handle `team_id` consistently with POST `/model/new` - [PR #15297](https://github.com/BerriAI/litellm/pull/15297) + - Feature: adds Infinity as a provider in the UI - [PR #15285](https://github.com/BerriAI/litellm/pull/15285) + - Fix: model + endpoints page crash when config file contains router_settings.model_group_alias - [PR #15308](https://github.com/BerriAI/litellm/pull/15308) + - Models & Endpoints Initial Refactor - [PR #15435](https://github.com/BerriAI/litellm/pull/15435) + - Litellm UI API Reference page updates - [PR #15438](https://github.com/BerriAI/litellm/pull/15438) + +- **Teams** + - Teams page: new column "Your Role" on the teams table - [PR #15384](https://github.com/BerriAI/litellm/pull/15384) + - LiteLLM Dashboard Teams UI refactor - [PR #15418](https://github.com/BerriAI/litellm/pull/15418) + +- **UI Infrastructure** + - Added prettier to autoformat frontend - [PR #15215](https://github.com/BerriAI/litellm/pull/15215) + - Adds turbopack to the npm run dev command in UI to build faster during development - [PR #15250](https://github.com/BerriAI/litellm/pull/15250) + - (perf) fix: Replaces bloated key list calls with lean key aliases endpoint - [PR #15252](https://github.com/BerriAI/litellm/pull/15252) + - Potentially fixes a UI spasm issue with an expired cookie - [PR #15309](https://github.com/BerriAI/litellm/pull/15309) + - LiteLLM UI Refactor Infrastructure - [PR #15236](https://github.com/BerriAI/litellm/pull/15236) + - Enforces removal of unused imports from UI - [PR #15416](https://github.com/BerriAI/litellm/pull/15416) + - Fix: usage page >> Model Activity >> spend per day graph: y-axis clipping on large spend values - [PR #15389](https://github.com/BerriAI/litellm/pull/15389) + - Updates guardrail provider logos - [PR #15421](https://github.com/BerriAI/litellm/pull/15421) + +- **Admin Settings** + - Fix: Router settings do not update despite success message - [PR #15249](https://github.com/BerriAI/litellm/pull/15249) + - Fix: Prevents DB from accidentally overriding config file values if they are empty in DB - [PR #15340](https://github.com/BerriAI/litellm/pull/15340) + +- **SSO** + - SSO - support EntraID app roles - [PR #15351](https://github.com/BerriAI/litellm/pull/15351) + +--- + +## Logging / Guardrail / Prompt Management Integrations + +#### Features + +- **[PostHog](../../docs/observability/posthog)** + - Feat: posthog per request api key - [PR #15379](https://github.com/BerriAI/litellm/pull/15379) + +#### Guardrails + +- **[EnkryptAI](../../docs/proxy/guardrails)** + - Add EnkryptAI Guardrails on LiteLLM - [PR #15390](https://github.com/BerriAI/litellm/pull/15390) + +--- + +## Spend Tracking, Budgets and Rate Limiting + +- **Tag Management** + - Tag Management - Add support for setting tag based budgets - [PR #15433](https://github.com/BerriAI/litellm/pull/15433) + +- **Dynamic Rate Limiter v3** + - QA/Fixes - Dynamic Rate Limiter v3 - final QA - [PR #15311](https://github.com/BerriAI/litellm/pull/15311) + - Fix dynamic Rate limiter v3 - inserting litellm_model_saturation - [PR #15394](https://github.com/BerriAI/litellm/pull/15394) + +- **Shared Health Check** + - Implement Shared Health Check State Across Pods - [PR #15380](https://github.com/BerriAI/litellm/pull/15380) + +--- + +## MCP Gateway + +- **Tool Control** + - MCP Gateway - UI - Select allowed tools for Key, Teams - [PR #15241](https://github.com/BerriAI/litellm/pull/15241) + - MCP Gateway - Backend - Allow storing allowed tools by team/key - [PR #15243](https://github.com/BerriAI/litellm/pull/15243) + - MCP Gateway - Fine-grained Database Object Storage Control - [PR #15255](https://github.com/BerriAI/litellm/pull/15255) + - MCP Gateway - Litellm mcp fixes team control - [PR #15304](https://github.com/BerriAI/litellm/pull/15304) + - MCP Gateway - QA/Fixes - Ensure Team/Key level enforcement works for MCPs - [PR #15305](https://github.com/BerriAI/litellm/pull/15305) + - Feature: Include server_name in /v1/mcp/server/health endpoint response - [PR #15431](https://github.com/BerriAI/litellm/pull/15431) + +- **OpenAPI Integration** + - MCP - support converting OpenAPI specs to MCP servers - [PR #15343](https://github.com/BerriAI/litellm/pull/15343) + - MCP - specify allowed params per tool - [PR #15346](https://github.com/BerriAI/litellm/pull/15346) + +- **Configuration** + - MCP - support setting CA_BUNDLE_PATH - [PR #15253](https://github.com/BerriAI/litellm/pull/15253) + - Fix: Ensure MCP client stays open during tool call - [PR #15391](https://github.com/BerriAI/litellm/pull/15391) + - Remove hardcoded "public" schema in migration.sql - [PR #15363](https://github.com/BerriAI/litellm/pull/15363) + +--- + +## Performance / Loadbalancing / Reliability improvements + +- **Router Optimizations** + - Fix - Router: add model_name index for O(1) deployment lookups - [PR #15113](https://github.com/BerriAI/litellm/pull/15113) + - Refactor Utils: extract inner function from client - [PR #15234](https://github.com/BerriAI/litellm/pull/15234) + - Fix Networking: remove limitations - [PR #15302](https://github.com/BerriAI/litellm/pull/15302) + +- **Session Management** + - Fix - Sessions not being shared - [PR #15388](https://github.com/BerriAI/litellm/pull/15388) + - Fix: remove panic from hot path - [PR #15396](https://github.com/BerriAI/litellm/pull/15396) + - Fix - shared session parsing and usage issue - [PR #15440](https://github.com/BerriAI/litellm/pull/15440) + - Fix: handle closed aiohttp sessions - [PR #15442](https://github.com/BerriAI/litellm/pull/15442) + - Fix: prevent session leaks when recreating aiohttp sessions - [PR #15443](https://github.com/BerriAI/litellm/pull/15443) + +- **SSL/TLS Performance** + - Perf: optimize SSL/TLS handshake performance with prioritized cipher - [PR #15398](https://github.com/BerriAI/litellm/pull/15398) + +- **Dependencies** + - Upgrades tenacity version to 8.5.0 - [PR #15303](https://github.com/BerriAI/litellm/pull/15303) + +- **Data Masking** + - Fix - SensitiveDataMasker converts lists to string - [PR #15420](https://github.com/BerriAI/litellm/pull/15420) + +--- + + +## General AI Gateway Improvements + +#### Security + +- **General** + - Fix: redact AWS credentials when redact_user_api_key_info enabled - [PR #15321](https://github.com/BerriAI/litellm/pull/15321) + +--- + +## Documentation Updates + +- **Provider Documentation** + - Update doc: perf update - [PR #15211](https://github.com/BerriAI/litellm/pull/15211) + - Add W&B Inference documentation - [PR #15278](https://github.com/BerriAI/litellm/pull/15278) + +- **Deployment** + - Deletion of docker-compose buggy comment that cause `config.yaml` based startup fail - [PR #15425](https://github.com/BerriAI/litellm/pull/15425) + +--- + +## New Contributors + +* @Gal-bloch made their first contribution in [PR #15219](https://github.com/BerriAI/litellm/pull/15219) +* @lcfyi made their first contribution in [PR #15315](https://github.com/BerriAI/litellm/pull/15315) +* @ashengstd made their first contribution in [PR #15362](https://github.com/BerriAI/litellm/pull/15362) +* @vkolehmainen made their first contribution in [PR #15363](https://github.com/BerriAI/litellm/pull/15363) +* @jlan-nl made their first contribution in [PR #15330](https://github.com/BerriAI/litellm/pull/15330) +* @BCook98 made their first contribution in [PR #15402](https://github.com/BerriAI/litellm/pull/15402) +* @PabloGmz96 made their first contribution in [PR #15425](https://github.com/BerriAI/litellm/pull/15425) + +--- + +## **[Full Changelog](https://github.com/BerriAI/litellm/compare/v1.77.7.rc.1...v1.78.0.rc.1)** +