..
chat
fix: add prompt_cache_key and prompt_cache_retention support for OpenAI
2026-02-24 16:42:54 -08:00
completion
fix(text_completion): support token IDs (list of integers) as prompt ( #18011 )
2026-01-12 17:33:24 +05:30
embeddings /guardrail_translation
[Fix] Guardrails API - Ensure OpenAI Moderations Guard works with OpenAI Embeddings ( #20523 )
2026-02-05 14:40:15 -08:00
evals
Update tests/test_litellm/llms/openai/evals/test_openai_evals_transformation.py
2026-02-17 19:30:58 +05:30
image_generation
test(image_generation): add tests for extra_headers propagation
2026-02-25 01:51:18 +08:00
realtime
[Feat] Add xAI /realtime API Support - works with LiveKitSDK ( #20381 )
2026-02-03 19:58:28 -08:00
responses
fix(responses): preserve query params in compact URL construction ( #22668 )
2026-03-04 11:33:13 -08:00
speech
fix(unified_guardrail.py): support during_call event type for unified guardrails ( #17514 )
2025-12-04 22:06:13 -08:00
transcriptions
test: use real completion_cost() instead of duplicating inline logic
2026-02-26 16:24:48 -03:00
vector_store_files
Vector store files Stable Release ( #16643 )
2025-11-15 13:00:33 -08:00
vector_stores
Fix create, search vector store error ( #13285 )
2025-08-06 11:15:17 -07:00
test_gpt5_transformation.py
feat(openai): drop reasoning_effort for gpt-5.4 when tools present
2026-03-06 22:20:47 +05:30
test_o_series_transformation.py
🐛 Fix a bug where openai image edit siltently ignores multiple images
2025-09-26 10:56:06 +05:30
test_openai_common_utils.py
fix: make LITELLM_CLIENT_SPECIFIC_PARAMS a tuple to prevent TypeError
2026-02-21 13:25:23 -08:00
test_openai_empty_response.py
(fix): empty response + vllm streaming ( #17516 )
2025-12-04 19:24:28 -08:00
test_openai_image_edit_transformation.py
fix(openai/image_edit/transformation.py): fix passing multiple images to openai
2025-09-27 16:03:17 -07:00