litellm/litellm
2025-07-03 16:45:38 -07:00
..
anthropic_interface [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
assistants Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (#9995) (#10423) 2025-04-29 21:27:37 -07:00
batch_completion
batches Store batch output file id in DB + Store batch file status in DB + (experimental) BATCH API COST TRACKING 2025-06-25 22:41:22 -07:00
caching [Bug Fix] No module named 'diskcache' (#11600) 2025-06-10 14:54:11 -07:00
completion_extras Azure - responses api bridge - respect responses/ + Gemini - generate content bridge - handle kwargs + litellm params containing stream (#12224) 2025-07-02 13:53:52 -07:00
endpoints/speech/speech_to_completion_bridge feat(speech/): working gemini tts support via openai's /v1/speech endpoint (#11832) 2025-06-18 10:36:25 -07:00
experimental_mcp_client added ruff fixes 2025-07-01 17:24:11 -07:00
files Litellm Unified File ID output file id support (#10713) 2025-05-10 11:02:09 -07:00
fine_tuning Litellm managed file updates combined (#11040) 2025-05-22 17:20:41 -07:00
google_genai [Bug Fix] Using gemini-cli with Vertex Anthropic Models (#12246) 2025-07-03 12:29:27 -07:00
images test: update tests 2025-05-24 12:26:31 -07:00
integrations Fix Deepeval logger debug formatting (#12303) 2025-07-03 16:45:38 -07:00
litellm_core_utils is_error_str_rate_limit 2025-07-03 16:03:48 -07:00
llms [Bug Fix] Using gemini-cli with Vertex Anthropic Models (#12246) 2025-07-03 12:29:27 -07:00
passthrough Bedrock Passthrough cost tracking (/invoke + /converse routes - streaming + non-streaming) (#12123) 2025-06-27 20:01:12 -07:00
proxy Litellm mcp tool prefix (#12289) 2025-07-03 11:39:37 -07:00
realtime_api Gemini Multimodal Live API support (#10841) 2025-05-15 22:39:09 -07:00
rerank_api feat: add HuggingFace rerank provider support (#11438) 2025-06-05 23:23:01 -07:00
responses Bug Fix - responses api fix got multiple values for keyword argument 'litellm_trace_id' (#12225) 2025-07-01 18:12:22 -07:00
router_strategy [Bug Fix] Using /messages with lowest latency routing (#12180) 2025-06-30 15:57:19 -07:00
router_utils [Bug fix] Router - handle cooldown_time = 0 for deployments (#12108) 2025-06-27 17:50:35 -07:00
secret_managers [️ Python SDK import] - reduce python sdk import time by .3s (#12140) 2025-06-28 14:57:10 -07:00
types Litellm dev fix gemini web search tracking (#12288) 2025-07-03 12:27:14 -07:00
vector_stores [Feat] OpenAI/Azure OpenAI - Add support for creating vector stores on LiteLLM (#12021) 2025-06-24 20:46:48 -07:00
__init__.py feat: Turn Mistral to use llm_http_handler (#12245) 2025-07-02 14:01:56 -07:00
_logging.py Fix: Initialize JSON logging for all loggers when JSON_LOGS=True (#12206) 2025-07-02 12:18:28 -07:00
_redis.py add _pretty_print_redis_config (#12073) 2025-06-26 10:26:57 -07:00
_service_logger.py [️ Python SDK import] - reduce python sdk import time by .3s (#12140) 2025-06-28 14:57:10 -07:00
_version.py
budget_manager.py
constants.py feat: Turn Mistral to use llm_http_handler (#12245) 2025-07-02 14:01:56 -07:00
cost_calculator.py Bedrock Passthrough cost tracking (/invoke + /converse routes - streaming + non-streaming) (#12123) 2025-06-27 20:01:12 -07:00
cost.json
exceptions.py [Feat] Add Lakera v2 Guardrail Support (#10880) 2025-05-16 17:08:21 -07:00
main.py [Bug Fix] Using gemini-cli with Vertex Anthropic Models (#12246) 2025-07-03 12:29:27 -07:00
model_prices_and_context_window_backup.json Add azure_ai cohere rerank v3.5 (#12283) 2025-07-03 10:01:45 -07:00
mypy.ini fix linting errors from ryptography.hazmat.bindings._rust 2025-05-17 16:31:30 -07:00
py.typed
router.py UI QA Fixes - prevent team model reset on model add + return team-only models on /v2/model/info + render team member budget correctly (#12144) 2025-06-28 22:04:49 -07:00
scheduler.py
timeout.py
utils.py [Bug Fix] Using gemini-cli with Vertex Anthropic Models (#12246) 2025-07-03 12:29:27 -07:00