* fix(anthropic/chat/transformation.py): Don't set tool choice on response_format conversion when thinking is enabled
Not allowed by Anthropic
Fixes https://github.com/BerriAI/litellm/issues/8901
* refactor: move test to base anthropic chat tests
ensures consistent behaviour across vertex/anthropic/bedrock
* fix(anthropic/chat/transformation.py): if thinking token is specified and max tokens is not - ensure max token to anthropic is higher than thinking tokens
* feat(converse_transformation.py): correctly handle thinking + response format on Bedrock Converse
Fixes https://github.com/BerriAI/litellm/issues/8901
* fix(converse_transformation.py): correctly handle adding max tokens
* test: handle service unavailable error
* fix(anthropic_claude3_transformation.py): fix amazon anthropic claude 3 tool calling transformation on invoke route
move to using anthropic config as base
* fix(utils.py): expose anthropic config via providerconfigmanager
* fix(llm_http_handler.py): support json mode on async completion calls
* fix(invoke_handler/make_call): support json mode for anthropic called via bedrock invoke
* fix(anthropic/): handle 'response_format: {"type": "text"}` + migrate amazon claude 3 invoke config to inherit from anthropic config
Prevents error when passing in 'response_format: {"type": "text"}
* test: fix test
* fix(utils.py): fix base invoke provider check
* fix(anthropic_claude3_transformation.py): don't pass 'stream' param
* fix: fix linting errors
* fix(converse_transformation.py): handle response_format type=text for converse
* fix(o_series_transformation.py): fix optional param check for o-series models
o3-mini and o-1 do not support parallel tool calling
* fix(utils.py): support 'drop_params' for 'thinking' param across models
allows switching to older claude versions (or non-anthropic models) and param to be safely dropped
* fix: fix passing thinking param in optional params
allows dropping thinking_param where not applicable
* test: update old model
* fix(utils.py): fix linting errors
* fix(main.py): add param to acompletion
* ui - use common team dropdown component
* re-use team component
* rename org field on add model
* handle add model submit
* working view model_id and team_id on root models page
* cleaner
* show all fields
* working model info view
* working team info selector
* clean up team id
* new component for model dashboard
* ui show table with dropdown
* make public model names like email
* revert changes to litellm model name
* fix litellm model name
* ui fix public model
* fix mappings
* fix conditional text input
* fix message
* ui fix bulk add models
* _add_team_model_to_db
* move model mgmt helper funcs
* test_add_team_model_to_db
* ui - display model team model name
* fix add model tab
* fix remove redundant info tab on models page
* dont pass model mappings all the way through
* fix jarring model name when adding team models
* fix edit model button
* delete button on model info
* ui fix model dashboard
* fix DeploymentTypedDict
* _is_model_access_group_for_wildcard_route
* test _get_public_model_name
* ui fix viewing public model name
* fix linting error
* fix linting errors
* fix selectedModel logic
* fix(azure/chat/gpt_transformation.py): add 'prediction' as a support azure param
Closes https://github.com/BerriAI/litellm/issues/8500
* build(model_prices_and_context_window.json): add new 'gemini-2.0-pro-exp-02-05' model
* style: cleanup invalid json trailing commma
* feat(utils.py): support passing 'tokenizer_config' to register_prompt_template
enables passing complete tokenizer config of model to litellm
Allows calling deepseek on bedrock with the correct prompt template
* fix(utils.py): fix register_prompt_template for custom model names
* test(test_prompt_factory.py): fix test
* test(test_completion.py): add e2e test for bedrock invoke deepseek ft model
* feat(base_invoke_transformation.py): support hf_model_name param for bedrock invoke calls
enables proxy admin to set base model for ft bedrock deepseek model
* feat(bedrock/invoke): support deepseek_r1 route for bedrock
makes it easy to apply the right chat template to that call
* feat(constants.py): store deepseek r1 chat template - allow user to get correct response from deepseek r1 without extra work
* test(test_completion.py): add e2e mock test for bedrock deepseek
* docs(bedrock.md): document new deepseek_r1 route for bedrock
allows us to use the right config
* fix(exception_mapping_utils.py): catch read operation timeout
* 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
* 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
* feat(health_check.py): set upperbound for api when making health check call
prevent bad model from health check to hang and cause pod restarts
* fix(health_check.py): cleanup task once completed
* fix(constants.py): bump default health check timeout to 1min
* docs(health.md): add 'health_check_timeout' to health docs on litellm
* build(proxy_server_config.yaml): add bad model to health check
* 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
* 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(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
* refactor(fireworks_ai/): inherit from openai like base config
refactors fireworks ai to use a common config
* test: fix import in test
* refactor(watsonx/): refactor watsonx to use llm base config
refactors chat + completion routes to base config path
* fix: fix linting error
* test: fix test
* fix: fix test
* feat(base_llm): initial commit for common base config class
Addresses code qa critique https://github.com/andrewyng/aisuite/issues/113#issuecomment-2512369132
* feat(base_llm/): add transform request/response abstract methods to base config class
* feat(cohere-+-clarifai): refactor integrations to use common base config class
* fix: fix linting errors
* refactor(anthropic/): move anthropic + vertex anthropic to use base config
* test: fix xai test
* test: fix tests
* fix: fix linting errors
* test: comment out WIP test
* fix(transformation.py): fix is pdf used check
* fix: fix linting error
* fix(main.py): support passing max retries to azure/openai embedding integrations
Fixes https://github.com/BerriAI/litellm/issues/7003
* feat(team_endpoints.py): allow updating team model aliases
Closes https://github.com/BerriAI/litellm/issues/6956
* feat(router.py): allow specifying model id as fallback - skips any cooldown check
Allows a default model to be checked if all models in cooldown
s/o @micahjsmith
* docs(reliability.md): add fallback to specific model to docs
* fix(utils.py): new 'is_prompt_caching_valid_prompt' helper util
Allows user to identify if messages/tools have prompt caching
Related issue: https://github.com/BerriAI/litellm/issues/6784
* feat(router.py): store model id for prompt caching valid prompt
Allows routing to that model id on subsequent requests
* fix(router.py): only cache if prompt is valid prompt caching prompt
prevents storing unnecessary items in cache
* feat(router.py): support routing prompt caching enabled models to previous deployments
Closes https://github.com/BerriAI/litellm/issues/6784
* test: fix linting errors
* feat(databricks/): convert basemodel to dict and exclude none values
allow passing pydantic message to databricks
* fix(utils.py): ensure all chat completion messages are dict
* (feat) Track `custom_llm_provider` in LiteLLMSpendLogs (#7081)
* add custom_llm_provider to SpendLogsPayload
* add custom_llm_provider to SpendLogs
* add custom llm provider to SpendLogs payload
* test_spend_logs_payload
* Add MLflow to the side bar (#7031)
Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
* (bug fix) SpendLogs update DB catch all possible DB errors for retrying (#7082)
* catch DB_CONNECTION_ERROR_TYPES
* fix DB retry mechanism for SpendLog updates
* use DB_CONNECTION_ERROR_TYPES in auth checks
* fix exp back off for writing SpendLogs
* use _raise_failed_update_spend_exception to ensure errors print as NON blocking
* test_update_spend_logs_multiple_batches_with_failure
* (Feat) Add StructuredOutputs support for Fireworks.AI (#7085)
* fix model cost map fireworks ai "supports_response_schema": true,
* fix supports_response_schema
* fix map openai params fireworks ai
* test_map_response_format
* test_map_response_format
* added deepinfra/Meta-Llama-3.1-405B-Instruct (#7084)
* bump: version 1.53.9 → 1.54.0
* fix deepinfra
* litellm db fixes LiteLLM_UserTable (#7089)
* ci/cd queue new release
* fix llama-3.3-70b-versatile
* refactor - use consistent file naming convention `AI21/` -> `ai21` (#7090)
* fix refactor - use consistent file naming convention
* ci/cd run again
* fix naming structure
* fix use consistent naming (#7092)
---------
Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Yuki Watanabe <31463517+B-Step62@users.noreply.github.com>
Co-authored-by: ali sayyah <ali.sayyah2@gmail.com>
* feat(router.py): add check for max fallback depth
Prevent infinite loop for fallbacks
Closes https://github.com/BerriAI/litellm/issues/6498
* test: update test
* (fix) Prometheus - Log Postgres DB latency, status on prometheus (#6484)
* fix logging DB fails on prometheus
* unit testing log to otel wrapper
* unit testing for service logger + prometheus
* use LATENCY buckets for service logging
* fix service logging
* docs clarify vertex vs gemini
* (router_strategy/) ensure all async functions use async cache methods (#6489)
* fix router strat
* use async set / get cache in router_strategy
* add coverage for router strategy
* fix imports
* fix batch_get_cache
* use async methods for least busy
* fix least busy use async methods
* fix test_dual_cache_increment
* test async_get_available_deployment when routing_strategy="least-busy"
* (fix) proxy - fix when `STORE_MODEL_IN_DB` should be set (#6492)
* set store_model_in_db at the top
* correctly use store_model_in_db global
* (fix) `PrometheusServicesLogger` `_get_metric` should return metric in Registry (#6486)
* fix logging DB fails on prometheus
* unit testing log to otel wrapper
* unit testing for service logger + prometheus
* use LATENCY buckets for service logging
* fix service logging
* fix _get_metric in prom services logger
* add clear doc string
* unit testing for prom service logger
* bump: version 1.51.0 → 1.51.1
* Add `azure/gpt-4o-mini-2024-07-18` to model_prices_and_context_window.json (#6477)
* Update utils.py (#6468)
Fixed missing keys
* (perf) Litellm redis router fix - ~100ms improvement (#6483)
* docs(exception_mapping.md): add missing exception types
Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183
* fix(main.py): register custom model pricing with specific key
Ensure custom model pricing is registered to the specific model+provider key combination
* test: make testing more robust for custom pricing
* fix(redis_cache.py): instrument otel logging for sync redis calls
ensures complete coverage for all redis cache calls
* refactor: pass parent_otel_span for redis caching calls in router
allows for more observability into what calls are causing latency issues
* test: update tests with new params
* refactor: ensure e2e otel tracing for router
* refactor(router.py): add more otel tracing acrosss router
catch all latency issues for router requests
* fix: fix linting error
* fix(router.py): fix linting error
* fix: fix test
* test: fix tests
* fix(dual_cache.py): pass ttl to redis cache
* fix: fix param
* perf(cooldown_cache.py): improve cooldown cache, to store cache results in memory for 5s, prevents redis call from being made on each request
reduces 100ms latency per call with caching enabled on router
* fix: fix test
* fix(cooldown_cache.py): handle if a result is None
* fix(cooldown_cache.py): add debug statements
* refactor(dual_cache.py): move to using an in-memory check for batch get cache, to prevent redis from being hit for every call
* fix(cooldown_cache.py): fix linting erropr
* build: merge main
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Xingyao Wang <xingyao@all-hands.dev>
Co-authored-by: vibhanshu-ob <115142120+vibhanshu-ob@users.noreply.github.com>
