BerriAI/litellm v1.75.5-stable.rc-draft

on GitHub

What's Changed

• [docs release notes] by @ishaan-jaff in #13237
• UI - Add giving keys prompt access by @krrishdholakia in #13233
• Prompt Management - Add table + prompt info page to UI by @krrishdholakia in #13232
• Prompt Management - add prompts on UI by @krrishdholakia in #13240
• [Proxy] Add OpenShift Support to non root docker image by @jugaldb in #13239
• [LLM Translation] Fix Model Usage not having text tokens by @jugaldb in #13234
• [UI] Add team deletion check for teams with keys by @jugaldb in #12953
• [Bug Fix] OpenAI / Azure Responses API - Add service_tier , safety_identifier supported params by @ishaan-jaff in #13258
• Bug Fix - Responses API raises error with Gemini Tool Calls in input by @ishaan-jaff in #13260
• Minor formatting changes to token-cost.json by @bbartels in #13244
• [Bug Fix] Fix Server root path regression on UI when using "Login" by @ishaan-jaff in #13267
• Support OCI provider by @breno-aumo in #13206
• Add GCS bucket caching support by @pascalwhoop in #13122
• Fix: Langfuse reporting "client closed" error due to httpx client TTL by @ZPerling in #13045
• [LLM Translation] Correct pricing for web search on 4o-mini by @jugaldb in #13269
• [Bug Fix] Prometheus - fix for litellm_input_tokens_metric, litellm_output_tokens_metric - Note this updates the metric name by @ishaan-jaff in #13271
• [LLM Translation] input cost per token higher than $1 test by @jugaldb in #13270
• [LLM Translation] Support /v1/models/{model_id} retrieval by @jugaldb in #13268
• [UI] - Add ability to set model alias per key/team by @ishaan-jaff in #13276
• fix OCI linting errors by @krrishdholakia in #13279
• Ensure disable_llm_api_endpoints works + Add wildcard model support for 'team-byok' model by @krrishdholakia in #13278
• fix(main.py): handle tool being a pydantic object + Fix unpack defs deepcopy issue for bedrock by @krrishdholakia in #13274
• Revert "Fix: Langfuse reporting "client closed" error due to httpx client TTL" by @ishaan-jaff in #13291
• [Redis] - Add ability to add client through GCP IAM Auth by @jugaldb in #13275
• [LLM Translation + Coding tools] Added litellm claude code count tokens support by @jugaldb in #13261
• [LLM Translation] claude opus 4.1 support for anthropic provider by @jugaldb in #13296
• [New model] add bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0 by @ishaan-jaff in #13295
• New models - add fireworks_ai/glm-4p5 model family by @ishaan-jaff in #13297
• [Feat] Add fireworks gpt-oss models by @ishaan-jaff in #13303
• Create New Key - Make Team Field Required for Service Account by @NANDINI-star in #13302
• [LLM Translation] Fix model group on clientside auth with API calls by @jugaldb in #13293
• [Redis IAM] Change documentation by @jugaldb in #13306
• [Proxy server] Add apscheduler log suppress by @jugaldb in #13299
• Fix double slash issue in SSO login URL construction by @NANDINI-star in #13289
• [MCP Gateway] refactor mcp guardrails by @jugaldb in #13238
• [Bug]: Fix Mimetype Resolution Error in Bedrock Document Understanding by @ishaan-jaff in #13309
• [Feat] - When using custom tags on prometheus allow using wildcard patterns by @ishaan-jaff in #13316
• [Bug Fix] [Bug]: New Databricks Foundation Models databricks-gpt-oss-20b and databricks-gpt-oss-120b failed with error: litellm.APIConnectionError: 'signature' by @ishaan-jaff in #13318
• [LLM Translation] Fix model group on clientside auth with API calls by @jugaldb in #13314
• fix(streaming_handler.py): include cost in streaming usage object by @krrishdholakia in #13319
• feat(JinaAI): support multimodal embedding models by @zjx20 in #13181
• Exclude none fields on /chat/completion - fixes n8n bug + Allow calling /v1/models when end user over budget by @krrishdholakia in #13320
• feat: Add logo customization for LiteLLM admin UI by @colesmcintosh in #12958
• [Feat] - New model - Add Bedrock gpt oss models - "openai.gpt-oss-20b-1:0", "openai.gpt-oss-120b-1:0" by @ishaan-jaff in #13342
• [MCP Gateway] fix auth on ui for bearer servers by @jugaldb in #13312
• Fix create, search vector store error by @yeahyung in #13285
• [Fix migration for MCP server name and alias] added new migration files by @jugaldb in #13345
• [MCP Gateway] Added route check for internal users by @jugaldb in #13350
• [UI]added token breakdown in ui by @jugaldb in #13357
• Feat - New models add groq/openai/gpt-oss by @ishaan-jaff in #13363
• Provider logos on usage page by @NANDINI-star in #13372
• feat(integrations): allow setting of braintrust callback base url by @edwarddamato in #13368
• fix: 12152 - Redacted sensitive information logged in guardrails by @AnandKhinvasara in #13356
• Add labels to migrations job template by @unique-jakub in #13343
• Update OCI docs by @breno-aumo in #13336
• [Feat] Responses API Session Handling - Multi media support by @ishaan-jaff in #13347
• Add GPT 5 models by @lowjiansheng in #13377
• feat - add claude-opus-4-1 on cost map by @ishaan-jaff in #13384
• feat: Add GPT-5 model family with official OpenAI specifications (#13… by @ishaan-jaff in #13386
• [Feat] add azure/gpt-5 model family by @ishaan-jaff in #13385
• Revert "Fix SSO Logout | Create Unified Login Page with SSO and Usern… by @ishaan-jaff in #13387
• Fix non-root docker image for migration by @1995parham in #13379
• [Bug Fix] Mistral Tool Calling - Grammar error: at 3(11): failed to compile JSON schema by @ishaan-jaff in #13389
• [Bug Fix] OpenAI gpt-5 series does not support "max_tokens" parameter and temperature values that are not = 1 by @ishaan-jaff in #13390
• Add presidio MCP pre call docs by @jugaldb in #13392
• [Bug Fix] Responses api session management for streaming responses by @ishaan-jaff in #13396
• Add Custom Tooltips to Model Mapping Table by @NANDINI-star in #13294
• feat(usage): Usage - Ensure Usage Page loads after the DB has large entries (aggregated user daily activity endpoint and UI integrati… by @ishaan-jaff in #13400
• Correct GPT-5 token limits and price by @emerzon in #13423
• fix(access group): allow access group on mcp tool retrieval by @thiagosalvatore in #13425
• fix(proxy): add missing braintrust api base to env vars by @edwarddamato in #13412
• [Feat] Add reasoning_effort to OpenAIGPT5Config by @ishaan-jaff in #13434
• [User Delete from team] fix user membership issue by @jugaldb in #13433
• Display Error from Backend on the UI - Notification by @NANDINI-star in #13427
• [Bug fix] - Error creating standard logging object - can't register atexit after shutdownLitellm fixes standard logging payload by @ishaan-jaff in #13436
• LLM Translation - fix prices for oai gpt 5 by @jugaldb in #13441
• Add support for reasoning_effort minimal by @lowjiansheng in #13401
• [Bug Fix] Improve error message from - key creation permission error message by @ishaan-jaff in #13443
• [Docs] Add docs on how router / cooldowns work by @ishaan-jaff in #13444
• LiteLLM UI - Test Key Page - allow uploading images for /chat/completions and /responses by @ishaan-jaff in #13445
• Disable logging settings for non-enterprise users - Create Key by @NANDINI-star in #13431
• feat(reasoning): support 'minimal' effort type for OpenAI by @colesmcintosh in #13447
• [Feat] Working e2e flow for Responses API session management with media by @ishaan-jaff in #13456
• [Documentation ]added mcp guardrails doc in mcp.md by @jugaldb in #13452
• feat(models): add OpenRouter and Cerebras GPT-OSS (20b, 120b) to cost map by @colesmcintosh in #13442
• docs - native LiteLLM prompt mgmt by @ishaan-jaff in #13463
• [Bug Fix] Responses API - Responses API failed if input containing ResponseReasoningItem by @ishaan-jaff in #13465
• [Bug Fix] - Get Routes by @ishaan-jaff in #13466
• [Bug Fix] /health checks should not use hardcoded trace_id by @ishaan-jaff in #13468
• [LLM Translation] Litellm azure o series drop params by @jugaldb in #13353
• [Proxy + UI] Litellm add reload model api and button by @jugaldb in #13464
• [Bug Fix] Allow using Swagger for /chat/completions by @ishaan-jaff in #13469
• Router - reduce p99 latency w/ redis enabled by 50% + OTEL - track pre_call hook latency by @krrishdholakia in #13362
• [Proxy changes] Litellm add model price reload schedule for multi-pod by @jugaldb in #13470
• [MCP Gateway] Add local storage auth for tokens by @jugaldb in #13473
• [Bug]: Fix JWTs access not working with model groups by @ishaan-jaff in #13474
• Add digitalocean provider by @msannan2 in #12169
• Model Hub - show price for azure models + Responses API - support custom tool by @krrishdholakia in #13418

New Contributors

• @bbartels made their first contribution in #13244
• @breno-aumo made their first contribution in #13206
• @pascalwhoop made their first contribution in #13122
• @ZPerling made their first contribution in #13045
• @zjx20 made their first contribution in #13181
• @edwarddamato made their first contribution in #13368
• @msannan2 made their first contribution in #12169

Full Changelog: v1.74.15-stable...v1.75.5-stable.rc-draft