From b9ba80897f442987def94864628e1ae19b1554c0 Mon Sep 17 00:00:00 2001 From: Shivam Rawat Date: Tue, 11 Aug 2026 17:27:11 -0700 Subject: [PATCH] docs(user endpoints): remove unsupported soft_budget param from user docstrings --- litellm/proxy/_types.py | 1 - litellm/proxy/management_endpoints/internal_user_endpoints.py | 2 -- 2 files changed, 3 deletions(-) diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py index 08348187645..4d04b401d83 100644 --- a/litellm/proxy/_types.py +++ b/litellm/proxy/_types.py @@ -4082,7 +4082,6 @@ class UserManagementEndpointParamDocStringEnums(str, enum.Enum): ) metadata_doc_str = """Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }""" max_parallel_requests_doc_str = """Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.""" - soft_budget_doc_str = """Optional[float] - Get alerts when user crosses given budget, doesn't block requests.""" model_max_budget_doc_str = """Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)""" model_rpm_limit_doc_str = """Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)""" model_tpm_limit_doc_str = """Optional[float] - Model-specific tpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)""" diff --git a/litellm/proxy/management_endpoints/internal_user_endpoints.py b/litellm/proxy/management_endpoints/internal_user_endpoints.py index a416a197ab8..8d5817f40f5 100644 --- a/litellm/proxy/management_endpoints/internal_user_endpoints.py +++ b/litellm/proxy/management_endpoints/internal_user_endpoints.py @@ -461,7 +461,6 @@ async def new_user( - permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking. - metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" } - max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x. - - soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests. - model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys) - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}. - model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys) @@ -1548,7 +1547,6 @@ async def user_update( - permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking. - metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" } - max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x. - - soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests. - model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys) - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}. - model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)