@@ -731,12 +731,7 @@ class GenerateRequestBase(LiteLLMPydanticObjectBase):
731
731
metadata : Optional [dict ] = {}
732
732
tpm_limit : Optional [int ] = None
733
733
rpm_limit : Optional [int ] = None
734
- rpm_limit_type : Optional [
735
- Literal ["guaranteed_throughput" , "best_effort_throughput" ]
736
- ] = None # raise an error if 'guaranteed_throughput' is set and we're overallocating rpm
737
- tpm_limit_type : Optional [
738
- Literal ["guaranteed_throughput" , "best_effort_throughput" ]
739
- ] = None # raise an error if 'guaranteed_throughput' is set and we're overallocating tpm
734
+
740
735
budget_duration : Optional [str ] = None
741
736
allowed_cache_controls : Optional [list ] = []
742
737
config : Optional [dict ] = {}
@@ -761,6 +756,12 @@ class KeyRequestBase(GenerateRequestBase):
761
756
tags : Optional [List [str ]] = None
762
757
enforced_params : Optional [List [str ]] = None
763
758
allowed_routes : Optional [list ] = []
759
+ rpm_limit_type : Optional [
760
+ Literal ["guaranteed_throughput" , "best_effort_throughput" ]
761
+ ] = None # raise an error if 'guaranteed_throughput' is set and we're overallocating rpm
762
+ tpm_limit_type : Optional [
763
+ Literal ["guaranteed_throughput" , "best_effort_throughput" ]
764
+ ] = None # raise an error if 'guaranteed_throughput' is set and we're overallocating tpm
764
765
765
766
766
767
class LiteLLMKeyType (str , enum .Enum ):
0 commit comments