diff --git a/litellm/proxy/management_endpoints/key_management_endpoints.py b/litellm/proxy/management_endpoints/key_management_endpoints.py index 52d06ffdb64..5cf92f34fab 100644 --- a/litellm/proxy/management_endpoints/key_management_endpoints.py +++ b/litellm/proxy/management_endpoints/key_management_endpoints.py @@ -1518,7 +1518,7 @@ async def generate_key_fn( - policies: Optional[List[str]] - List of policy names to apply to the key. Policies define guardrails, conditions, and inheritance rules. - disable_global_guardrails: Optional[bool] - Whether to disable global guardrails for the key. - throttle_on_budget_exceeded: Optional[bool] - When the key exceeds its max_budget, throttle its tpm/rpm to the global budget_exceeded_throttle_percentage instead of blocking the key entirely. - - permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false} It may also carry an `access_schedule` object ({"timezone": "Europe/Berlin", "windows": [{"days": ["mon","tue"], "start": "09:00", "end": "18:00"}]}) restricting the key to recurring time windows; requests outside every window are rejected with 403 + - permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false} - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget. - 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[dict] - key-specific model rpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific rpm limit. @@ -1727,7 +1727,7 @@ async def generate_service_account_key_fn( - 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. - metadata: Optional[dict] - Metadata for key, store information for key. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" } - guardrails: Optional[List[str]] - List of active guardrails for the key - - permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false} It may also carry an `access_schedule` object ({"timezone": "Europe/Berlin", "windows": [{"days": ["mon","tue"], "start": "09:00", "end": "18:00"}]}) restricting the key to recurring time windows; requests outside every window are rejected with 403 + - permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false} - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget. - 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[dict] - key-specific model rpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific rpm limit.