[Feat] Allow using litellm.completion with /v1/messages API Spec (use gpt-4, gemini etc with claude code) ( #11502 )
2025-06-06 20:35:53 -07:00
Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE ( #9995 ) ( #10423 )
2025-04-29 21:27:37 -07:00
(code quality) run ruff rule to ban unused imports ( #7313 )
2024-12-19 12:33:42 -08:00
(feat)Litellm x twelvelabs bedrock[Async Invoke Support] ( #14871 )
2025-10-02 18:52:33 -07:00
[Fix] Cache - Avoiding expensive operations when cache isn't available ( #15182 )
2025-10-04 09:10:37 -07:00
fix: fix import errors
2025-09-14 09:32:21 -07:00
endpoints/speech /speech_to_completion_bridge
fix: fix import errors
2025-09-14 09:32:21 -07:00
fix: resolve regression with duplicate Mcp-Protocol-Version header
2025-09-30 07:12:56 +09:00
Litellm gemini batch ( #14733 )
2025-09-19 15:22:52 -07:00
Litellm managed file updates combined ( #11040 )
2025-05-22 17:20:41 -07:00
fix test /generateContent route
2025-10-04 10:49:46 -07:00
Revert " #14404 BugFix - Add support for Azure AD token-based authorization in image generation request headers definition for Azure"
2025-09-24 16:23:20 +05:30
OTEL fix spans
2025-10-04 09:22:57 -07:00
Merge branch 'main' into litellm_dev_09_30_2025_p1
2025-10-04 14:15:55 -07:00
fix: prevent session leaks when recreating aiohttp sessions
2025-10-10 17:34:47 -07:00
test fix location of encode bedrock runtime modelid arn
2025-08-22 17:34:09 -07:00
add: shared connection fix
2025-10-09 17:12:09 -07:00
[LLM Translation] Fix Realtime API endpoint for no intent ( #13476 )
2025-08-14 16:24:14 -07:00
[Feat] Add Nvidia NIM Rerank Support ( #15152 )
2025-10-02 18:58:52 -07:00
[Feat] Return Cost for Responses API Streaming requests ( #15053 )
2025-09-29 19:47:04 -07:00
fix: remove router inefficiencies (from O(M*N) to O(1)) - 62.5% faster P99 latency ( #15046 )
2025-09-29 15:49:46 -07:00
fix: fix import errors
2025-09-14 09:32:21 -07:00
fix: use fastuuid helper ( #14903 )
2025-09-25 15:47:01 -07:00
Fix: Add shared_session to all_litellm_params to prevent JSON serialization error
2025-10-10 13:22:38 -07:00
[Bug Fix] Bedrock KB - Using LiteLLM Managed Credentials for Query ( #13787 )
2025-08-19 15:39:36 -07:00
ci/cd new release
2025-10-04 12:49:52 -07:00
[Feat] Add support for returning images with gemini/gemini-2.5-flash-image-preview with /chat/completions ( #13983 )
2025-08-27 16:16:19 -07:00
[Security] Fix: Ensure .info() logs are not used for request/responses + Add code QA check for possible violations ( #14386 )
2025-09-09 13:55:56 -07:00
[ ⚡ ️ Python SDK import] - reduce python sdk import time by .3s ( #12140 )
2025-06-28 14:57:10 -07:00
Fix: revert fastuuid optional dependency, always use fastuuid in .__uid helper ( #14941 )
2025-09-26 09:14:20 -07:00
Virtual key based policies in Aim Guardrails ( #9499 )
2025-04-01 21:57:23 -07:00
Squashed commit of the following: ( #9709 )
2025-04-02 21:24:54 -07:00
add: suggest fast algorithms
2025-10-09 17:23:42 -07:00
Removing get_model_info from Lemonade provider. Implemented get_models which gets hooked into get_valid_models litellm utility. Also, added a simple cost calculator implementation for Lemonade so calling cost_calculator.completion_cost() doesn't return an error when a model is not found in the model_cost json.
2025-09-30 12:12:24 -06:00
Revert "[Feature]: Replace HTTPException with ParallelRequestLimitError in pa…" ( #15095 )
2025-09-30 21:17:04 -07:00
Fix: Add shared_session support for embedding calls with connection pooling
2025-10-10 13:47:39 -07:00
Fix "azure_ai/grok-4-fast-reasoning" entry in "model_prices_and_context_window.json" ( #15204 )
2025-10-04 14:50:44 -07:00
fix mypy
2025-09-27 12:21:32 -07:00
[Fix] - Router: optimize unhealthy deployment filtering in retry path (O(n*m) → O(n+m)) ( #15110 )
2025-10-02 18:55:18 -07:00
Squashed commit of the following: ( #9709 )
2025-04-02 21:24:54 -07:00
Litellm ruff linting enforcement ( #5992 )
2024-10-01 19:44:20 -04:00
[Fix] Cache - Avoiding expensive operations when cache isn't available ( #15182 )
2025-10-04 09:10:37 -07:00
daab207a95