litellm/tests/local_testing/test_spend_calculate_endpoint.py
yuneng-jiang 4f93e2c3da
test: point CircleCI-only suites at models still in the cost map (#42617)
* test: point CircleCI-only suites at models still in the cost map

#42435 removed cost map entries past their deprecation date and #42437 added
litellm_uisettings to the config-synced tables, but both only updated
tests/test_litellm. The CircleCI-only suites (local_testing, llm_translation,
logging_callback_tests, litellm_utils_tests, unit) kept using the removed
models or the old table list and went red on main.

Each test keeps its assertions and swaps the removed model for a current one
with the same provider and capabilities. The fireworks tests pick a vision
model from the cost map because #34941 set supports_vision false on
minimax-m3, and the vertex image provider test injects the image model set
because #42435 removed every vertex_ai-image-models entry.

* test(vertex_ai): register the image model through add_known_models in the provider test
2026-09-22 17:28:34 -07:00

136 lines
3.6 KiB
Python

import pytest
from dotenv import load_dotenv
from fastapi import Request
from fastapi.routing import APIRoute
import litellm
from litellm.proxy._types import SpendCalculateRequest
from litellm.proxy.spend_tracking.spend_management_endpoints import calculate_spend
from litellm.router import Router
# this file is to test litellm/proxy
@pytest.mark.asyncio
async def test_spend_calc_model_messages():
cost_obj = await calculate_spend(
request=SpendCalculateRequest(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": "What is the capital of France?"},
],
)
)
print("calculated cost", cost_obj)
cost = cost_obj["cost"]
assert cost > 0.0
@pytest.mark.asyncio
async def test_spend_calc_model_on_router_messages():
from litellm.proxy.proxy_server import llm_router as init_llm_router
temp_llm_router = Router(
model_list=[
{
"model_name": "special-llama-model",
"litellm_params": {
"model": "groq/openai/gpt-oss-20b",
},
}
]
)
setattr(litellm.proxy.proxy_server, "llm_router", temp_llm_router)
cost_obj = await calculate_spend(
request=SpendCalculateRequest(
model="special-llama-model",
messages=[
{"role": "user", "content": "What is the capital of France?"},
],
)
)
print("calculated cost", cost_obj)
_cost = cost_obj["cost"]
assert _cost > 0.0
# set router to init value
setattr(litellm.proxy.proxy_server, "llm_router", init_llm_router)
@pytest.mark.asyncio
async def test_spend_calc_using_response():
cost_obj = await calculate_spend(
request=SpendCalculateRequest(
completion_response={
"id": "chatcmpl-3bc7abcd-f70b-48ab-a16c-dfba0b286c86",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Yooo! What's good?",
"role": "assistant",
},
}
],
"created": "1677652288",
"model": "groq/openai/gpt-oss-20b",
"object": "chat.completion",
"system_fingerprint": "fp_873a560973",
"usage": {
"completion_tokens": 8,
"prompt_tokens": 12,
"total_tokens": 20,
},
}
)
)
print("calculated cost", cost_obj)
cost = cost_obj["cost"]
assert cost > 0.0
@pytest.mark.asyncio
async def test_spend_calc_model_alias_on_router_messages():
from litellm.proxy.proxy_server import llm_router as init_llm_router
temp_llm_router = Router(
model_list=[
{
"model_name": "gpt-4o",
"litellm_params": {
"model": "gpt-4o",
},
}
],
model_group_alias={
"gpt4o": "gpt-4o",
},
)
setattr(litellm.proxy.proxy_server, "llm_router", temp_llm_router)
cost_obj = await calculate_spend(
request=SpendCalculateRequest(
model="gpt4o",
messages=[
{"role": "user", "content": "What is the capital of France?"},
],
)
)
print("calculated cost", cost_obj)
_cost = cost_obj["cost"]
assert _cost > 0.0
# set router to init value
setattr(litellm.proxy.proxy_server, "llm_router", init_llm_router)