| .. |
|
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
|
|
|
|
batch_completion
|
|
|
|
batches
|
UI - Support 'batch' model health checks + make 'team-only' model concept clearer (#12770)
|
2025-07-19 14:30:38 -07:00 |
|
caching
|
[LLM Translation - Redis] fix: redis caching for embedding response models (#12750)
|
2025-07-18 16:31:10 -07:00 |
|
completion_extras
|
fix: remove unused imports in completion_extras transformation (#12655)
|
2025-07-16 10:23:13 -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
|
[MCP Gateway] Litellm mcp client list fail (#13114)
|
2025-07-30 15:23:19 -07:00 |
|
files
|
|
|
|
fine_tuning
|
|
|
|
google_genai
|
[Bug Fix] Gemini-CLI Integration - ensure tool calling works as expected on generateContent (#13189)
|
2025-07-31 16:42:57 -07:00 |
|
images
|
[Feat] Add Google AI Studio Imagen4 model family (#13065)
|
2025-07-28 21:25:40 -07:00 |
|
integrations
|
Prompt Management - abstract prompt templates away from model list (enables permission management on prompt templates) (#13219)
|
2025-08-02 09:39:45 -07:00 |
|
litellm_core_utils
|
Prompt Management (2/2) - New /prompt/list endpoint + key-based access to prompt templates (#13218)
|
2025-08-02 10:36:38 -07:00 |
|
llms
|
Revert "fix: role chaining and session name with webauthentication for aws be…" (#13230)
|
2025-08-02 10:11:58 -07:00 |
|
passthrough
|
Bedrock Passthrough cost tracking (/invoke + /converse routes - streaming + non-streaming) (#12123)
|
2025-06-27 20:01:12 -07:00 |
|
proxy
|
ruff fix
|
2025-08-02 12:43:01 -07:00 |
|
realtime_api
|
[LLM Translation] fix query params for realtime api intent (#12838)
|
2025-07-25 10:09:53 -07:00 |
|
rerank_api
|
Add Hosted VLLM rerank provider integration (#12738)
|
2025-07-18 10:55:50 -07:00 |
|
responses
|
[MCP Gateway] Litellm mcp pre and during guardrails (#13188)
|
2025-08-01 20:02:25 -07:00 |
|
router_strategy
|
[Feat] UI - Allow Adding LiteLLM Auto Router on UI (#12960)
|
2025-07-24 19:58:49 -07:00 |
|
router_utils
|
Fix async retryer on .acompletion() + forward clientside headers - filter out content-type from clientside request (causes llm api call to hang) (#12886)
|
2025-07-22 19:50:05 -07:00 |
|
secret_managers
|
Added handling for pwd protected cert files in AOAI CertificateCredential auth (#12995)
|
2025-07-28 21:34:54 -07:00 |
|
types
|
Prompt Management (2/2) - New /prompt/list endpoint + key-based access to prompt templates (#13218)
|
2025-08-02 10:36:38 -07:00 |
|
vector_stores
|
[Feat] LLM API Endpoint - Expose OpenAI Compatible /vector_stores/{vector_store_id}/search endpoint (#12749)
|
2025-07-18 18:18:53 -07:00 |
|
__init__.py
|
Prompt Management - abstract prompt templates away from model list (enables permission management on prompt templates) (#13219)
|
2025-08-02 09:39:45 -07:00 |
|
_logging.py
|
suppress httpx logging (#13217)
|
2025-08-01 20:02:08 -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] - Track cost + add tags for health checks done by LiteLLM Proxy (#12880)
|
2025-07-22 18:45:57 -07:00 |
|
cost_calculator.py
|
Anthropic - mid stream fallbacks p2 (add token usage across both calls) (#13170)
|
2025-07-31 21:28:06 -07:00 |
|
cost.json
|
|
|
|
exceptions.py
|
Anthropic - working mid-stream fallbacks (#13149)
|
2025-07-31 21:22:49 -07:00 |
|
main.py
|
Fix missing extra_headers support for vLLM/openai_like embeddings (#13198)
|
2025-08-02 08:56:06 -07:00 |
|
model_prices_and_context_window_backup.json
|
add openrouter grok4 (#13018)
|
2025-07-29 14:24:33 -07:00 |
|
mypy.ini
|
|
|
|
py.typed
|
|
|
|
router.py
|
Anthropic - mid stream fallbacks p2 (add token usage across both calls) (#13170)
|
2025-07-31 21:28:06 -07:00 |
|
scheduler.py
|
|
|
|
timeout.py
|
|
|
|
utils.py
|
Fix - using managed files w/ OTEL + UI - add model group alias on UI (#13171)
|
2025-07-31 21:22:04 -07:00 |
