scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 89

test(azure): cover data-zone gpt-4o-2024-11-20 cache read pricing (absorbed from #37996)

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-24 13:13:53 +00:00
parent c5da8eb41c
commit 451d826e1d
1 changed files with 24 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
tests/test_litellm/llms/azure/test_azure_cost_calculation.py
View file

@ -6,7 +6,8 @@ import pytest
import litellm
from litellm.llms.azure.cost_calculation import cost_per_token
from litellm.types.utils import Usage
from litellm.types.utils import PromptTokensDetailsWrapper, Usage
from litellm.utils import get_model_info
# Register a test model with tier-specific pricing
@ -73,3 +74,25 @@ class TestAzureServiceTierCostCalculation:
assert abs(none_prompt - standard_prompt) < 1e-10
assert abs(none_completion - standard_completion) < 1e-10
@pytest.mark.parametrize(
"model",
["azure/us/gpt-4o-2024-11-20", "azure/eu/gpt-4o-2024-11-20"],
)
def test_gpt4o_2024_11_20_data_zone_cache_read_cost(model, local_model_cost_map):
model_info = get_model_info(model=model, custom_llm_provider="azure")
assert model_info["cache_read_input_token_cost"] == 1.375e-06
assert model_info["input_cost_per_token"] == 2.75e-06
assert model_info["output_cost_per_token"] == 1.1e-05
usage = Usage(
prompt_tokens=6000,
completion_tokens=10,
total_tokens=6010,
prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5000),
)
prompt_cost, completion_cost = cost_per_token(model=model, usage=usage)
assert prompt_cost == pytest.approx((1000 * 2.75e-06) + (5000 * 1.375e-06))
assert completion_cost == pytest.approx(10 * 1.1e-05)