* fix(azure.py): ensure max_retries=0 is respected
Fixes https://github.com/BerriAI/litellm/issues/6129
* fix(test_openai.py): add unit test to ensure openai sdk calls always respect max_retries = 0
* test(test_azure_openai.py): add unit testing for azure_text/ route
* fix(azure.py): fix passing max retries on streaming
* fix(azure.py): fix azure max retries on async completion + streaming
* fix(completion/handler.py): fix azure text async completion + streaming
* test(test_azure_openai.py): ensure azure openai max retries always respected
* test(test_azure_o_series.py): add testing to ensure max retries always respected
* Added gemini providers for 2.0-flash and 2.0-flash lite (#8321)
* Update model_prices_and_context_window.json
added gemini providers for 2.0-flash and 2.0-flash light
* Update model_prices_and_context_window.json
fixed URL
---------
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* Convert tool use arguments to string before counting tokens (#6989)
In at least some cases the `messages["tool_calls"]["function"]["arguments"]` is a dict, not a string. In order to tokenize it properly it needs to be a string. In the case that it is already a string this is a noop, which is also fine.
* build(model_prices_and_context_window.json): add gemini 2.0 flash lite pricing
* build(model_prices_and_context_window.json): add gemini commercial rate limits
* fix(utils.py): fix linting error
* refactor(utils.py): refactor to maintain function size
---------
Co-authored-by: Bardia Khosravi <bardiakhosravi95@gmail.com>
Co-authored-by: Josh Morrow <josh@jcmorrow.com>
* fix(utils.py): handle key error in msg validation
* Support running Aim Guard during LLM call (#7918)
* support running Aim Guard during LLM call
* Rename header
* adjust docs and fix type annotations
* fix(timeout.md): doc fix for openai example on dynamic timeouts
---------
Co-authored-by: Tomer Bin <117278227+hxtomer@users.noreply.github.com>
* initial transform for invoke
* invoke transform_response
* working - able to make request
* working get_complete_url
* working - invoke now runs on llm_http_handler
* fix unused imports
* track litellm overhead ms
* working stream request
* sign_request transform
* sign_request update
* use has_async_custom_stream_wrapper property
* use get_async_custom_stream_wrapper in base llm http handler
* fix make_call in invoke handler
* fix invoke with streaming get_async_custom_stream_wrapper
* working bedrock async streaming with invoke
* fix make call handler for bedrock
* test_all_model_configs
* fix test_bedrock_custom_prompt_template
* sync streaming for bedrock invoke
* fix _add_stream_param_to_request_body
* test_async_text_completion_bedrock
* fix transform_request
* fix get_supported_openai_params
* fix test supports tool choice
* fix test_supports_tool_choice
* add unit test coverage for bedrock invoke transform
* fix location of transformation files
* update import loc
* fix bedrock invoke unit tests
* fix import for max completion tokens
* fix(o_series_transformation.py): add 'reasoning_effort' as o series model param
Closes https://github.com/BerriAI/litellm/issues/8182
* fix(main.py): ensure `reasoning_effort` is a mapped openai param
* refactor(azure/): rename o1_[x] files to o_series_[x]
* refactor(base_llm_unit_tests.py): refactor testing for o series reasoning effort
* test(test_azure_o_series.py): have azure o series tests correctly inherit from base o series model tests
* feat(base_utils.py): support translating 'developer' role to 'system' role for non-openai providers
Makes it easy to switch from openai to anthropic
* fix: fix linting errors
* fix(base_llm_unit_tests.py): fix test
* fix(main.py): add missing param
* fix: support azure o3 model family for fake streaming workaround (#8162)
* fix: support azure o3 model family for fake streaming workaround
* refactor: rename helper to is_o_series_model for clarity
* update function calling parameters for o3 models (#8178)
* refactor(o1_transformation.py): refactor o1 config to be o series config, expand o series model check to o3
ensures max_tokens is correctly translated for o3
* feat(openai/): refactor o1 files to be 'o_series' files
expands naming to cover o3
* fix(azure/chat/o1_handler.py): azure openai is an instance of openai - was causing resets
* test(test_azure_o_series.py): assert stream faked for azure o3 mini
Resolves https://github.com/BerriAI/litellm/pull/8162
* fix(o1_transformation.py): fix o1 transformation logic to handle explicit o1_series routing
* docs(azure.md): update doc with `o_series/` model name
---------
Co-authored-by: byrongrogan <47910641+byrongrogan@users.noreply.github.com>
Co-authored-by: Low Jian Sheng <15527690+lowjiansheng@users.noreply.github.com>
* add support for using llama spec with bedrock
* fix get_bedrock_invoke_provider
* add support for using bedrock provider in mappings
* working request
* test_bedrock_custom_deepseek
* test_bedrock_custom_deepseek
* fix _get_model_id_for_llama_like_model
* test_bedrock_custom_deepseek
* doc DeepSeek-R1-Distill-Llama-70B
* test_bedrock_custom_deepseek
* Litellm dev 01 29 2025 p4 (#8107)
* fix(key_management_endpoints.py): always get db team
Fixes https://github.com/BerriAI/litellm/issues/7983
* test(test_key_management.py): add unit test enforcing check_db_only is always true on key generate checks
* test: fix test
* test: skip gemini thinking
* Litellm dev 01 29 2025 p3 (#8106)
* fix(__init__.py): reduces size of __init__.py and reduces scope for errors by using correct param
* refactor(__init__.py): refactor init by cleaning up redundant params
* refactor(__init__.py): move more constants into constants.py
cleanup root
* refactor(__init__.py): more cleanup
* feat(__init__.py): expose new 'disable_hf_tokenizer_download' param
enables hf model usage in offline env
* docs(config_settings.md): document new disable_hf_tokenizer_download param
* fix: fix linting error
* fix: fix unsafe comparison
* test: fix test
* docs(public_teams.md): add doc showing how to expose public teams for users to join
* docs: add beta disclaimer on public teams
* test: update tests
* docs: cleanup doc
* feat(bedrock/): initial commit adding bedrock/converse_like/<model> route support
allows routing to a converse like endpoint
Resolves https://github.com/BerriAI/litellm/issues/8085
* feat(bedrock/chat/converse_transformation.py): make converse config base config compatible
enables new 'converse_like' route
* feat(converse_transformation.py): enables using the proxy with converse like api endpoint
Resolves https://github.com/BerriAI/litellm/issues/8085
* refactor _add_callbacks_from_db_config
* fix check for _custom_logger_exists_in_litellm_callbacks
* move loc of test utils
* run ci/cd again
* test_add_custom_logger_callback_to_specific_event_with_duplicates_callbacks
* fix _custom_logger_class_exists_in_success_callbacks
* unit testing for test_add_callbacks_from_db_config
* test_custom_logger_exists_in_callbacks_individual_functions
* fix config.yml
* fix test test_stream_chunk_builder_openai_audio_output_usage - use direct dict comparison
* 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
* fix(utils.py): handle failed hf tokenizer request during calls
prevents proxy from failing due to bad hf tokenizer calls
* fix(utils.py): convert failure callback str to custom logger class
Fixes https://github.com/BerriAI/litellm/issues/8013
* test(test_utils.py): fix test - avoid adding mlflow dep on ci/cd
* fix: add missing env vars to test
* test: cleanup redundant test
* fix(utils.py): initial commit fixing custom cost tracking
refactors out provider specific model info from `get_model_info` - this was causing custom costs to be registered incorrectly
* fix(utils.py): cleanup `_supports_factory` to check provider info, if model info is None
some providers support features like vision across all models
* fix(utils.py): refactor to use _supports_factory
* test: update testing
* fix: fix linting errors
* test: fix testing
* 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
* fix(bedrock/converse_handler.py): fix bedrock region name on async calls
* fix(utils.py): fix split model handling
Fixes bedrock cost calculation when region name is given
* feat(_health_endpoints.py): support health checking datadog integration
Closes https://github.com/BerriAI/litellm/issues/7921
* feat(router.py): add retry headers to response
makes it easy to add testing to ensure model-specific retries are respected
* fix(add_retry_headers.py): clarify attempted retries vs. max retries
* test(test_fallbacks.py): add test for checking if max retries set for model is respected
* test(test_fallbacks.py): assert values for attempted retries and max retries are as expected
* fix(utils.py): return timeout in litellm proxy response headers
* test(test_fallbacks.py): add test to assert model specific timeout used on timeout error
* test: add bad model with timeout to proxy
* fix: fix linting error
* fix(router.py): fix get model list from model alias
* test: loosen test restriction - account for other events on proxy
* fix(utils.py): move adding custom logger callback to success event into separate function + don't add success callback to failure event
if user is explicitly choosing 'success' callback, don't log failure as well
* test(test_utils.py): add unit test to ensure custom logger callback only adds callback to specific event
* fix(utils.py): remove string from list of callbacks once corresponding callback class is added
prevents floating values - simplifies testing
* fix(utils.py): fix linting error
* test: cleanup args before test
* test: fix test
* test: update test
* test: fix test
* 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
* fix(initial-test-to-return-api-timeout-value-in-openai-timeout-exception): Makes it easier for user to debug why request timed out
* feat(openai.py): return timeout value + time taken on openai timeout errors
helps debug timeout errors
* fix(utils.py): fix num retries extraction logic when num_retries = 0
* fix(config_settings.md): litellm_logging.py
support printing payload to console if 'LITELLM_PRINT_STANDARD_LOGGING_PAYLOAD' is true
Enables easier debug
* test(test_auth_checks.py'): remove common checks userapikeyauth enforcement check
* fix(litellm_logging.py): fix linting error
* build: ensure all regional bedrock models have same supported values as base bedrock model
prevents drift
* test(base_llm_unit_tests.py): add testing for nested pydantic objects
* fix(test_utils.py): add test_get_potential_model_names
* fix(anthropic/chat/transformation.py): support nested pydantic objects
Fixes https://github.com/BerriAI/litellm/issues/7755
* fix(gpt_transformation.py): fix response_format translation check for 4o models
Fixes https://github.com/BerriAI/litellm/issues/7616
* feat(key_management_endpoints.py): support 'temp_budget_increase' and 'temp_budget_expiry' fields
Allow proxy admin to grant temporary budget increases to keys
* fix(proxy/_types.py): enforce temp_budget_increase and temp_budget_expiry are always passed together
* feat(user_api_key_auth.py): initial working temp budget increase logic
ensures key budget exceeded error checks for temp budget in key metadata
* feat(proxy_server.py): return the key max budget and key spend in the response headers
Allows clientside user to know their remaining limits
* test: add unit testing for new proxy utils
Ensures new key budget is correctly handled
* docs(temporary_budget_increase.md): add doc on temporary budget increase
* fix(utils.py): remove 3.5 from response_format check for now
not all azure 3.5 models support response_format
* fix(user_api_key_auth.py): return valid user api key auth object on all paths
* use lru cache wrapper
* use lru_cache_wrapper for _cached_get_model_info_helper
* fix _get_traceback_str_for_error
* huggingface/mistralai/Mistral-7B-Instruct-v0.3
* 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
* test(test_get_model_info.py): add unit test confirming router deployment updates global 'get_model_info'
* fix(get_supported_openai_params.py): fix custom llm provider 'get_supported_openai_params'
Fixes https://github.com/BerriAI/litellm/issues/7668
* docs(azure.md): clarify how azure ad token refresh on proxy works
Closes https://github.com/BerriAI/litellm/issues/7665
* 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(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
* test(test_utils.py): initial test for valid models
Addresses https://github.com/BerriAI/litellm/issues/7525
* fix: test
* feat(fireworks_ai/transformation.py): support retrieving valid models from fireworks ai endpoint
* refactor(fireworks_ai/): support checking model info on `/v1/models` route
* docs(set_keys.md): update docs to clarify check llm provider api usage
* fix(watsonx/common_utils.py): support 'WATSONX_ZENAPIKEY' for iam auth
* fix(watsonx): read in watsonx token from env var
* fix: fix linting errors
* fix(utils.py): fix provider config check
* style: cleanup unused imports
* 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
* fix(langfuse_prompt_management.py): migrate dynamic logging to langfuse custom logger compatible class
* fix(langfuse_prompt_management.py): support failure callback logging to langfuse as well
* feat(proxy_server.py): support setting custom tokenizer on config.yaml
Allows customizing value for `/utils/token_counter`
* fix(proxy_server.py): fix linting errors
* test: skip if file not found
* style: cleanup unused import
* docs(configs.md): add docs on setting custom tokenizer
