phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(proxy_server.py): new /spend/calculate endpoint

Browse source 
Allows user to calculate spend before making the call
This commit is contained in:
Krrish Dholakia 2024-03-27 17:08:55 -07:00
parent 62e557404c
commit 4da70d223e
1 changed files with 74 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

77
litellm/proxy/proxy_server.py
View file

@ -4343,7 +4343,7 @@ async def info_key_fn(
@router.get(
"/spend/keys",
tags=["budget & spend Tracking"],
tags=["Budget & Spend Tracking"],
dependencies=[Depends(user_api_key_auth)],
)
async def spend_key_fn():
@ -4375,7 +4375,7 @@ async def spend_key_fn():
@router.get(
"/spend/users",
tags=["budget & spend Tracking"],
tags=["Budget & Spend Tracking"],
dependencies=[Depends(user_api_key_auth)],
)
async def spend_user_fn(
@ -4427,7 +4427,7 @@ async def spend_user_fn(
@router.get(
"/spend/tags",
tags=["budget & spend Tracking"],
tags=["Budget & Spend Tracking"],
dependencies=[Depends(user_api_key_auth)],
responses={
200: {"model": List[LiteLLM_SpendLogs]},
@ -4500,6 +4500,77 @@ async def view_spend_tags(
)
@router.post(
"/spend/calculate",
tags=["Budget & Spend Tracking"],
dependencies=[Depends(user_api_key_auth)],
responses={
200: {
"cost": {
"description": "The calculated cost",
"example": 0.0,
"type": "float",
}
}
},
)
async def calculate_spend(request: Request):
"""
Accepts all the params of completion_cost.
Calculate spend **before** making call:
```
curl --location 'http://localhost:4000/spend/calculate'
--header 'Authorization: Bearer sk-1234'
--header 'Content-Type: application/json'
--data '{
"model": "anthropic.claude-v2",
"messages": [{"role": "user", "content": "Hey, how'''s it going?"}]
}'
```
Calculate spend **after** making call:
```
curl --location 'http://localhost:4000/spend/calculate'
--header 'Authorization: Bearer sk-1234'
--header 'Content-Type: application/json'
--data '{
"completion_response": {
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"model": "gpt-3.5-turbo-0125",
"system_fingerprint": "fp_44709d6fcb",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello there, how may I assist you today?"
},
"logprobs": null,
"finish_reason": "stop"
}]
"usage": {
"prompt_tokens": 9,
"completion_tokens": 12,
"total_tokens": 21
}
}
}'
```
"""
from litellm import completion_cost
data = await request.json()
if "completion_response" in data:
data["completion_response"] = litellm.ModelResponse(
**data["completion_response"]
)
return {"cost": completion_cost(**data)}
@router.get(
"/spend/logs",
tags=["Budget & Spend Tracking"],