* docs(reliability.md): add doc on disabling fallbacks per request
* feat(litellm_pre_call_utils.py): support reading request timeout from request headers - new `x-litellm-timeout` param
Allows setting dynamic model timeouts from vercel's AI sdk
* test(test_proxy_server.py): add simple unit test for reading request timeout
* test(test_fallbacks.py): add e2e test to confirm timeout passed in request headers is correctly read
* feat(main.py): support passing metadata to openai in preview
Resolves https://github.com/BerriAI/litellm/issues/6022#issuecomment-2616119371
* fix(main.py): fix passing openai metadata
* docs(request_headers.md): document new request headers
* build: Merge branch 'main' into litellm_dev_01_27_2025_p3
* test: loosen test
* feat(main.py): use asyncio.sleep for mock_Timeout=true on async request
adds unit testing to ensure proxy does not fail if specific Openai requests hang (e.g. recent o1 outage)
* fix(streaming_handler.py): fix deepseek r1 return reasoning content on streaming
Fixes https://github.com/BerriAI/litellm/issues/7942
* Revert "fix(streaming_handler.py): fix deepseek r1 return reasoning content on streaming"
This reverts commit 7a052a64e3.
* fix(deepseek-r-1): return reasoning_content as a top-level param
ensures compatibility with existing tools that use it
* fix: fix linting error
* test(test_completion_cost.py): add sdk test to ensure base model is used for cost tracking
* test(test_completion_cost.py): add sdk test to ensure custom pricing works
* fix(main.py): add base model cost tracking support for embedding calls
Enables base model cost tracking for embedding calls when base model set as a litellm_param
* fix(litellm_logging.py): update logging object with litellm params - including base model, if given
ensures base model param is always tracked
* fix(main.py): fix linting errors
* fix(http_handler.py): support passing ssl verify dynamically and using the correct httpx client based on passed ssl verify param
Fixes https://github.com/BerriAI/litellm/issues/6499
* feat(llm_http_handler.py): support passing `ssl_verify=False` dynamically in call args
Closes https://github.com/BerriAI/litellm/issues/6499
* fix(proxy/utils.py): prevent bad logs from breaking all cost tracking + reset list regardless of success/failure
prevents malformed logs from causing all spend tracking to break since they're constantly retried
* test(test_proxy_utils.py): add test to ensure bad log is dropped
* test(test_proxy_utils.py): ensure in-memory spend logs reset after bad log error
* test(test_user_api_key_auth.py): add unit test to ensure end user id as str works
* fix(auth_utils.py): ensure extracted end user id is always a str
prevents db cost tracking errors
* test(test_auth_utils.py): ensure get end user id from request body always returns a string
* test: update tests
* test: skip bedrock test- behaviour now supported
* test: fix testing
* refactor(spend_tracking_utils.py): reduce size of get_logging_payload
* test: fix test
* bump: version 1.59.4 → 1.59.5
* Revert "bump: version 1.59.4 → 1.59.5"
This reverts commit 1182b46b2e.
* fix(utils.py): fix spend logs retry logic
* fix(spend_tracking_utils.py): fix get tags
* fix(spend_tracking_utils.py): fix end user id spend tracking on pass-through endpoints
* feat(main.py): add new 'provider_specific_header' param
allows passing extra header for specific provider
* fix(litellm_pre_call_utils.py): add unit test for pre call utils
* test(test_bedrock_completion.py): skip test now that bedrock supports this
* fix(utils.py): don't pass 'anthropic-beta' header to vertex - will cause request to fail
* fix(utils.py): add flag to allow user to disable filtering invalid headers
ensure user can control behaviour
* style(utils.py): cleanup message
* test(test_utils.py): add unit test to cover invalid header filtering
* fix(proxy_server.py): fix custom openapi schema generation
* fix(utils.py): pass extra headers if set
* fix(main.py): fix image variation to use 'client' param
* feat(main.py): initial commit for `/image/variations` endpoint support
* refactor(base_llm/): introduce new base llm base config for image variation endpoints
* refactor(openai/image_variations/transformation.py): implement openai image variation transformation handler
* fix: test
* feat(openai/): working openai `/image/variation` endpoint calls via sdk
* feat(topaz/): topaz sync image variation call support
Addresses https://github.com/BerriAI/litellm/issues/7593
'
* fix(topaz/transformation.py): fix linting errors
* fix(openai/image_variations/handler.py): fix passing json data
* fix(main.py): image_variation/
support async image variation route - `aimage_variation`
* fix(test_get_model_info.py): fix test
* fix: cleanup unused imports
* feat(openai/): add async `/image/variations` endpoint support
* feat(topaz/): support async `/image/variations` calls
* fix: test
* fix(utils.py): fix get_model_info_helper for no model info w/ provider config
handles situation where model info is not known but provider config exists
* test(test_router_fallbacks.py): mark flaky test
* fix: fix unused imports
* test: bump otel load test perf threshold - accounts for current load tests hitting same server
* fix(__init__.py): fix init to exclude pricing-only model cost values from real model names
prevents bad health checks on wildcard routes
* fix(get_llm_provider.py): fix to handle calling bedrock_converse models
* feat(langfuse.py): log the used prompt when prompt management used
* test: fix test
* docs(self_serve.md): add doc on restricting personal key creation on ui
* feat(s3.py): support s3 logging with team alias prefixes (if available)
New preview feature
* fix(main.py): remove old if block - simplify to just await if coroutine returned
fixes lm_studio async embedding error
* fix(langfuse.py): handle get prompt check
* fix(vertex_ai/gemini/transformation.py): handle 'http://' in gemini process url
* refactor(router.py): refactor '_prompt_management_factory' to use logging obj get_chat_completion logic
deduplicates code
* fix(litellm_logging.py): update 'get_chat_completion_prompt' to update logging object messages
* docs(prompt_management.md): update prompt management to be in beta
given feedback - this still needs to be revised (e.g. passing in user message, not ignoring)
* refactor(prompt_management_base.py): introduce base class for prompt management
allows consistent behaviour across prompt management integrations
* feat(prompt_management_base.py): support adding client message to template message + refactor langfuse prompt management to use prompt management base
* fix(litellm_logging.py): log prompt id + prompt variables to langfuse if set
allows tracking what prompt was used for what purpose
* feat(litellm_logging.py): log prompt management metadata in standard logging payload + use in langfuse
allows logging prompt id / prompt variables to langfuse
* test: fix test
* fix(router.py): cleanup unused imports
* fix: fix linting error
* fix: fix trace param typing
* fix: fix linting errors
* fix: fix code qa check
* fix(main.py): fix lm_studio/ embedding routing
adds the mapping + updates docs with example
* docs(self_serve.md): update doc to show how to auto-add sso users to teams
* fix(streaming_handler.py): simplify async iterator check, to just check if streaming response is an async iterable
* fix(custom_logger.py): expose new 'async_get_chat_completion_prompt' event hook
* fix(custom_logger.py): langfuse_prompt_management.py
remove 'headers' from custom logger 'async_get_chat_completion_prompt' and 'get_chat_completion_prompt' event hooks
* feat(router.py): expose new function for prompt management based routing
* feat(router.py): partial working router prompt factory logic
allows load balanced model to be used for model name w/ langfuse prompt management call
* feat(router.py): fix prompt management with load balanced model group
* feat(langfuse_prompt_management.py): support reading in openai params from langfuse
enables user to define optional params on langfuse vs. client code
* test(test_Router.py): add unit test for router based langfuse prompt management
* fix: fix linting errors
* fix(types/utils.py): support langfuse + humanloop routes on llm router
* fix(main.py): remove acompletion elif block
just await if coroutine returned
* test(azure_openai_o1.py): initial commit with testing for azure openai o1 preview model
* fix(base_llm_unit_tests.py): handle azure o1 preview response format tests
skip as o1 on azure doesn't support tool calling yet
* fix: initial commit of azure o1 handler using openai caller
simplifies calling + allows fake streaming logic alr. implemented for openai to just work
* feat(azure/o1_handler.py): fake o1 streaming for azure o1 models
azure does not currently support streaming for o1
* feat(o1_transformation.py): support overriding 'should_fake_stream' on azure/o1 via 'supports_native_streaming' param on model info
enables user to toggle on when azure allows o1 streaming without needing to bump versions
* style(router.py): remove 'give feedback/get help' messaging when router is used
Prevents noisy messaging
Closes https://github.com/BerriAI/litellm/issues/5942
* fix(types/utils.py): handle none logprobs
Fixes https://github.com/BerriAI/litellm/issues/328
* fix(exception_mapping_utils.py): fix error str unbound error
* refactor(azure_ai/): move to openai_like chat completion handler
allows for easy swapping of api base url's (e.g. ai.services.com)
Fixes https://github.com/BerriAI/litellm/issues/7275
* refactor(azure_ai/): move to base llm http handler
* fix(azure_ai/): handle differing api endpoints
* fix(azure_ai/): make sure all unit tests are passing
* fix: fix linting errors
* fix: fix linting errors
* fix: fix linting error
* fix: fix linting errors
* fix(azure_ai/transformation.py): handle extra body param
* fix(azure_ai/transformation.py): fix max retries param handling
* fix: fix test
* test(test_azure_o1.py): fix test
* fix(llm_http_handler.py): support handling azure ai unprocessable entity error
* fix(llm_http_handler.py): handle sync invalid param error for azure ai
* fix(azure_ai/): streaming support with base_llm_http_handler
* fix(llm_http_handler.py): working sync stream calls with unprocessable entity handling for azure ai
* fix: fix linting errors
* fix(llm_http_handler.py): fix linting error
* fix(azure_ai/): handle cohere tool call invalid index param error
* test(azure_openai_o1.py): initial commit with testing for azure openai o1 preview model
* fix(base_llm_unit_tests.py): handle azure o1 preview response format tests
skip as o1 on azure doesn't support tool calling yet
* fix: initial commit of azure o1 handler using openai caller
simplifies calling + allows fake streaming logic alr. implemented for openai to just work
* feat(azure/o1_handler.py): fake o1 streaming for azure o1 models
azure does not currently support streaming for o1
* feat(o1_transformation.py): support overriding 'should_fake_stream' on azure/o1 via 'supports_native_streaming' param on model info
enables user to toggle on when azure allows o1 streaming without needing to bump versions
* style(router.py): remove 'give feedback/get help' messaging when router is used
Prevents noisy messaging
Closes https://github.com/BerriAI/litellm/issues/5942
* test: fix azure o1 test
* test: fix tests
* fix: fix test
* docs(sidebar.js): docs for support model access groups for wildcard routes
* feat(key_management_endpoints.py): add check if user is premium_user when adding model access group for wildcard route
* refactor(docs/): make control model access a root-level doc in proxy sidebar
easier to discover how to control model access on litellm
* docs: more cleanup
* feat(fireworks_ai/): add document inlining support
Enables user to call non-vision models with images/pdfs/etc.
* test(test_fireworks_ai_translation.py): add unit testing for fireworks ai transform inline helper util
* docs(docs/): add document inlining details to fireworks ai docs
* feat(fireworks_ai/): allow user to dynamically disable auto add transform inline
allows client-side disabling of this feature for proxy users
* feat(fireworks_ai/): return 'supports_vision' and 'supports_pdf_input' true on all fireworks ai models
now true as fireworks ai supports document inlining
* test: fix tests
* fix(router.py): add unit testing for _is_model_access_group_for_wildcard_route
* feat(deepgram/): initial e2e support for deepgram stt
Uses deepgram's `/listen` endpoint to transcribe speech to text
Closes https://github.com/BerriAI/litellm/issues/4875
* fix: fix linting errors
* test: fix test
* feat(main.py): mock_response() - support 'litellm.ContextWindowExceededError' in mock response
enabled quicker router/fallback/proxy debug on context window errors
* feat(exception_mapping_utils.py): extract special litellm errors from error str if calling `litellm_proxy/` as provider
Closes https://github.com/BerriAI/litellm/issues/7259
* fix(user_api_key_auth.py): specify 'Received Proxy Server Request' is span kind server
Closes https://github.com/BerriAI/litellm/issues/7298
* test: add new test image embedding to base llm unit tests
Addresses https://github.com/BerriAI/litellm/issues/6515
* fix(bedrock/embed/multimodal-embeddings): strip data prefix from image urls for bedrock multimodal embeddings
Fix https://github.com/BerriAI/litellm/issues/6515
* feat: initial commit for fireworks ai audio transcription support
Relevant issue: https://github.com/BerriAI/litellm/issues/7134
* test: initial fireworks ai test
* feat(fireworks_ai/): implemented fireworks ai audio transcription config
* fix(utils.py): register fireworks ai audio transcription config, in config manager
* fix(utils.py): add fireworks ai param translation to 'get_optional_params_transcription'
* refactor(fireworks_ai/): define text completion route with model name handling
moves model name handling to specific fireworks routes, as required by their api
* refactor(fireworks_ai/chat): define transform_Request - allows fixing model if accounts/ is missing
* fix: fix linting errors
* fix: fix linting errors
* fix: fix linting errors
* fix: fix linting errors
* fix(handler.py): fix linting errors
* fix(main.py): fix tgai text completion route
* refactor(together_ai/completion): refactors together ai text completion route to just use provider transform request
* refactor: move test_fine_tuning_api out of local_testing
reduces local testing ci/cd time
* run azure testing on ci/cd
* update docs on azure batches endpoints
* add input azure.jsonl
* refactor - use separate file for batches endpoints
* fixes for passing custom llm provider to /batch endpoints
* pass custom llm provider to files endpoints
* update azure batches doc
* add info for azure batches api
* update batches endpoints
* use simple helper for raising proxy exception
* update config.yml
* fix imports
* add type hints to get_litellm_params
* update get_litellm_params
* update get_litellm_params
* update get slp
* QOL - stop double logging a create batch operations on custom loggers
* re use slp from og event
* _create_standard_logging_object_for_completed_batch
* fix linting errors
* reduce num changes in PR
* update BATCH_STATUS_POLL_MAX_ATTEMPTS
* fix(main.py): support 'mock_timeout=true' param
allows mock requests on proxy to have a time delay, for testing
* fix(main.py): ensure mock timeouts raise litellm.Timeout error
triggers retry/fallbacks
* fix: fix fallback + mock timeout testing
* fix(router.py): always return remaining tpm/rpm limits, if limits are known
allows for rate limit headers to be guaranteed
* docs(timeout.md): add docs on mock timeout = true
* fix(main.py): fix linting errors
* test: fix test
* fix(hosted_vllm/transformation.py): return fake api key, if none give. Prevents httpx error
Fixes https://github.com/BerriAI/litellm/issues/7291
* test: fix test
* fix(main.py): add hosted_vllm/ support for embeddings endpoint
Closes https://github.com/BerriAI/litellm/issues/7290
* docs(vllm.md): add docs on vllm embeddings usage
* fix(__init__.py): fix sambanova model test
* fix(base_llm_unit_tests.py): skip pydantic obj test if model takes >5s to respond
* fix(main.py): fix retries being multiplied when using openai sdk
Closes https://github.com/BerriAI/litellm/pull/7130
* docs(prompt_management.md): add langfuse prompt management doc
* feat(team_endpoints.py): allow teams to add their own models
Enables teams to call their own finetuned models via the proxy
* test: add better enforcement check testing for `/model/new` now that teams can add their own models
* docs(team_model_add.md): tutorial for allowing teams to add their own models
* test: fix test
* fix(azure/): support passing headers to azure openai endpoints
Fixes https://github.com/BerriAI/litellm/issues/6217
* fix(utils.py): move default tokenizer to just openai
hf tokenizer makes network calls when trying to get the tokenizer - this slows down execution time calls
* fix(router.py): fix pattern matching router - add generic "*" to it as well
Fixes issue where generic "*" model access group wouldn't show up
* fix(pattern_match_deployments.py): match to more specific pattern
match to more specific pattern
allows setting generic wildcard model access group and excluding specific models more easily
* fix(proxy_server.py): fix _delete_deployment to handle base case where db_model list is empty
don't delete all router models b/c of empty list
Fixes https://github.com/BerriAI/litellm/issues/7196
* fix(anthropic/): fix handling response_format for anthropic messages with anthropic api
* fix(fireworks_ai/): support passing response_format + tool call in same message
Addresses https://github.com/BerriAI/litellm/issues/7135
* Revert "fix(fireworks_ai/): support passing response_format + tool call in same message"
This reverts commit 6a30dc6929.
* test: fix test
* fix(replicate/): fix replicate default retry/polling logic
* test: add unit testing for router pattern matching
* test: update test to use default oai tokenizer
* test: mark flaky test
* test: skip flaky test
* fix(acompletion): support fallbacks on acompletion
allows health checks for wildcard routes to use fallback models
* test: update cohere generate api testing
* add max tokens to health check (#7000)
* fix: fix health check test
* test: update testing
---------
Co-authored-by: Cameron <561860+wallies@users.noreply.github.com>
