phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(proxy_server.py): expose new /model_group/info endpoint

Browse source 
returns model-group level info on supported params, max tokens, pricing, etc.
This commit is contained in:
Krrish Dholakia 2024-05-26 14:07:35 -07:00
parent bec13d465a
commit 22b6b99b34
6 changed files with 191 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

15
litellm/types/router.py
View file

@ -411,3 +411,18 @@ class AlertingConfig(BaseModel):
webhook_url: str
alerting_threshold: Optional[float] = 300
class ModelGroupInfo(BaseModel):
model_group: str
providers: List[str]
max_input_tokens: Optional[float] = None
max_output_tokens: Optional[float] = None
input_cost_per_token: Optional[float] = None
output_cost_per_token: Optional[float] = None
mode: Literal[
"chat", "embedding", "completion", "image_generation", "audio_transcription"
]
supports_parallel_function_calling: bool = Field(default=False)
supports_vision: bool = Field(default=False)
supports_function_calling: bool = Field(default=False)

10
litellm/types/utils.py
View file

@ -12,3 +12,13 @@ class ProviderField(TypedDict):
field_type: Literal["string"]
field_description: str
field_value: str
class ModelInfo(TypedDict):
max_tokens: int
max_input_tokens: int
max_output_tokens: int
input_cost_per_token: float
output_cost_per_token: float
litellm_provider: str
mode: str