d6cd50dfdb
feat: Add support for custom Anthropic-compatible API endpoints
...
This commit adds support for custom Anthropic-compatible API endpoints
that don't follow the standard /v1/messages or /v1/complete path convention.
## Changes
- Added LITELLM_ANTHROPIC_DISABLE_URL_SUFFIX environment variable
- When set to true, prevents automatic appending of /v1/messages (for anthropic)
- When set to true, prevents automatic appending of /v1/complete (for anthropic_text)
- Added debug logging to indicate when suffix is being skipped
- Maintained full backward compatibility - existing deployments are unaffected
2025-08-26 01:22:51 +08:00
d95578464e
Add support for AWS assume_role with a session token
2025-08-23 22:37:21 -07:00
e0e356e328
test mapped test fixes
2025-08-23 17:04:23 -07:00
0fccd619ea
test_vertex_ai_deepseek
2025-08-23 14:13:03 -07:00
cf64033044
test fix
2025-08-23 14:04:41 -07:00
f1c710a608
test_e2e_generate_cold_storage_object_key_not_configured
2025-08-23 13:33:33 -07:00
b9132968b2
[Perf] Improvements for Async Success Handler (Logging Callbacks) - Approx +130 RPS ( #13905 )
...
* [Performance] Reduce Significant CPU overhead from litellm_logging.py (#13895 )
* fix: litellm.configured_cold_storage_logger
* fix Session Management - Non-OpenAI Models docs
* ruff fix
* test fix
* create LoggingWorker
* add GLOBAL_LOGGING_WORKER for async task handling
* fix logging tests
* add conftest
* fix conftest
* test fix location of encode bedrock runtime modelid arn
* fix conftest.py
* tuning LoggingWorker
* conftest.py
* fix conftest batches/
* test_async_chat_azure
* event_loop
* test_bedrock_streaming_passthrough_test2
* fix GLOBAL_LOGGING_WORKER
* logging worker
* add flush for global logging worker
* Revert "fix GLOBAL_LOGGING_WORKER"
This reverts commit d254f508f48935652f054777652938ad71976cce.
* fix conftest clear_queue
* fix conftest clear_queue
* setup_and_teardown for llm translation
* docs AWS_REGION
* test_async_chat_azure
* change test DIR
* run ci/cd again
* use 1 job for litellm_router_unit_testing
* fix space
* fix litellm_router_unit_testing
* test_aaarouter_dynamic_cooldown_message_retry_time
* litellm_router_unit_testing
* conftest.py clearing qu
* fixes litellm_router_unit_testing
* fixes clear_queue
* fix router_unit_tests
* remove conftest
* add back conftest for router
* fix event loop test
* test fix
* fixes for LoggingWorker
* ruff fix
2025-08-23 13:13:23 -07:00
9750374081
[Feat] New LLM API - AI/ML API for Image Gen ( #13893 )
...
* add LlmProviders.AIML
* add AIMLChatConfig
* add aiml
* fix AimlImageGenerationConfig
* add AimlImageGenerationConfig
* add cost_calculator
* fixes for AI ML API
* add known AIML Flux image models
* add AIML Cost Calc
* add AI/ML API
* add aiml_models
2025-08-23 13:12:44 -07:00
9df6f4ef08
Merge branch 'main' into litellm_dev_08_20_2025_p1
2025-08-23 12:09:53 -07:00
b23e35f75e
test: update tests
2025-08-23 12:09:19 -07:00
ef66bb87b3
Merge branch 'main' into litellm_dev_08_16_2025_p2
2025-08-23 11:30:51 -07:00
385bb15219
test: skip test
2025-08-23 11:27:46 -07:00
06a2915e9f
Merge pull request #13671 from BerriAI/litellm_dev_08_15_2025_p1
...
Responses API - support `allowed_openai_params` + Mistral - handle empty assistant content + support new mistral 'thinking' response block
2025-08-23 11:15:23 -07:00
4d7433b5ad
test: reduce mistral direct tests b/c of rate limit errors
2025-08-23 11:15:03 -07:00
cbb161f10b
test: handle internal server errors
2025-08-23 11:00:18 -07:00
f0b0ee51e0
Merge branch 'main' into litellm_dev_08_15_2025_p1
2025-08-23 10:51:56 -07:00
ba9f6894b7
test: update tests
2025-08-23 10:42:41 -07:00
3e764ec268
Merge pull request #13808 from mainred/validate_api_version
...
feat(utils.py): accept 'api_version' as param for validate_environment
2025-08-22 23:59:38 -07:00
867b48a24f
Merge pull request #13866 from jinskjoy/Mistral-File-ID
...
[Enhancement] Add support for Mistral model file handling and update documentation
2025-08-22 23:54:17 -07:00
825d6b08f0
test fix location of encode bedrock runtime modelid arn
2025-08-22 17:34:09 -07:00
56c16fc6f6
[Performance] Reduce Significant CPU overhead from litellm_logging.py ( #13895 )
...
* fix: litellm.configured_cold_storage_logger
* fix Session Management - Non-OpenAI Models docs
* ruff fix
* test fix
2025-08-22 16:17:57 -07:00
3c1dcb64cc
fix by adding init lock ( #13666 )
2025-08-22 11:42:43 -07:00
dcad39c00f
Merge pull request #13753 from RichardoC/fix-bedrock-irsa-role-assumption
...
fix: role chaining and session name with webauthentication for aws bedrock
2025-08-22 07:20:27 -07:00
59e43595b9
Merge pull request #13852 from michal-otmianowski/async-s3-implementation
...
Async s3 implementation
2025-08-21 23:19:51 -07:00
8b45e53878
Merge pull request #13880 from datarobot-forks/carsongee/improve_datarobot_api_handling
...
🐛 Bug Fix: Updated URL handling for DataRobot provider URL
2025-08-21 23:18:40 -07:00
9c4a86e98e
Merge pull request #13868 from kankute-sameer/litellm_feat_voyage_context_3_embedding_model
...
[Feat] Add support for voyage-context-3 embedding model
2025-08-21 23:18:20 -07:00
6214d22126
Merge pull request #13863 from luizrennocosta/fix/pll-req-lim-v3-api-key
...
fix: fixing descriptor/response size mismatch on parallel_request_limiter_v3
2025-08-21 23:14:04 -07:00
e93e266f84
[Performance] Use O(1) Set lookups for model routing ( #13879 )
...
* o(1) lookups
* Revert "o(1) lookups"
This reverts commit 620d14246980813366b4b1f1c0ce396b528dd9df.
* o(1) lookups
* Revert "o(1) lookups"
This reverts commit 676a9f5bcc3c2b9fa31e0a9fdf00389739b3052f.
* o(1) lookups
* register_model fix
* test_aget_valid_models
* lambda ai models fix
* test_utils.py
* test fix vertex ai
2025-08-21 22:56:46 -07:00
a61275f6e2
Merge pull request #13796 from 0x-fang/fix_aip_pass_through_08_20
...
Fix(Bedrock): fix application inference profile for pass-through endpoints for bedrock
2025-08-21 19:41:23 -07:00
b46de0ab5c
Updated URL handling for DataRobot provider base
2025-08-21 19:42:46 -06:00
7c2c1c11d9
Merge pull request #13783 from philipkiely-baseten/main
...
Update Baseten LiteLLM integration
2025-08-21 18:34:36 -07:00
77a5de37b1
[Fix] Ensure Service Account Keys require team_id field on API Endpoints ( #13873 )
...
* fixes for generating service accounts through the API
* fixes for test_update_service_account_works_with_team_id
2025-08-21 14:55:06 -07:00
5ac4fb512c
Add support for voyage-context-3 embedding model
2025-08-22 00:15:12 +05:30
d8a33e137d
[Enhancement] Add support for Mistral model file handling and update documentation
2025-08-21 20:35:07 +02:00
5fa4a18073
add testing and remove redundant function
2025-08-21 11:25:26 -07:00
f8711200d0
fix: fixing descriptor/response size difference when indexing descriptor
2025-08-21 13:43:23 -03:00
a6f052882b
fix test
2025-08-21 12:10:29 +02:00
feae09da5d
minor adjustments
2025-08-21 11:33:11 +02:00
5dd7e00127
formatting adjustments
2025-08-21 11:27:12 +02:00
08c942c306
refactor tests
2025-08-21 10:38:43 +02:00
744dca1dc3
init asyc implementation
2025-08-21 10:22:54 +02:00
0e6e8af1c3
Merge pull request #13795 from TomeHirata/feat/predict/mlflow
...
Include predicted output in MLflow tracing
2025-08-20 22:40:33 -07:00
1f84451925
Merge pull request #13803 from UlookEE/fix_bedrock_epc_acompletion
...
fix : Synchronize cache behavior between acompletion and completion
2025-08-20 22:38:30 -07:00
ff267ab68e
Merge pull request #13820 from kankute-sameer/litellm_rerank_deepinfra_endpoint
...
Add rerank endpoint support for deepinfra
2025-08-20 22:33:25 -07:00
609679ded4
Merge pull request #13835 from 0x-fang/fix_api_key_guardrail_proxy
...
Fix(bedrock): fix the api key support for bedrock guardrail in proxy
2025-08-20 22:31:17 -07:00
07f6235730
[Performance] Improve LiteLLM Python SDK RPS by +200 RPS ( #13839 )
...
* fix _proxy_from_env +100 RPS
* fix: global_braintrust_http_handler
* test_braintrust_logging
2025-08-20 21:46:33 -07:00
91040b6b56
fix the api key support for bedrock guardrail in proxy
2025-08-20 18:46:00 -07:00
34ad646101
fix(auth_checks.py): handle both flows + add unit tests
2025-08-20 16:42:08 -07:00
e5c3e006c2
fix(proxy_server.py): fix merge config + db router settings logic
2025-08-20 16:33:31 -07:00
55dcaded72
[Feat] Add VertexAI qwen API Service ( #13828 )
...
* add support for vertex AI QWEN API
* streaming QWEN API support
* test_partner_models_httpx
* test_partner_models_httpx_streaming
* add cost tracking for vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maa
* docs qwen models vertexAI
2025-08-20 15:00:33 -07:00
0x5751