scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-13 08:52:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 175

test: restore azure ai cached-token billing coverage with derived rates
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-09-17 22:49:02 +00:00
parent 0b58281038
commit 91619376d2
1 changed files with 17 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py
View file

@ -350,3 +350,20 @@ class TestAzureAIServiceTierCostCalculation:
assert flex_prompt < standard_prompt
assert flex_completion < standard_completion
@pytest.mark.parametrize("model", ["Codestral-2501", "MAI-Thinking-1"])
def test_azure_ai_cached_tokens_bill_at_the_entry_rates(local_model_cost_map, model: str) -> None:
info: Final = litellm.get_model_info(model=model, custom_llm_provider="azure_ai")
usage: Final = Usage(
prompt_tokens=1000,
completion_tokens=500,
total_tokens=1500,
prompt_tokens_details={"cached_tokens": 400},
)
prompt_cost, response_completion_cost = cost_per_token(model=model, usage=usage)
cache_read_rate: Final = info.get("cache_read_input_token_cost") or 0.0
assert prompt_cost == pytest.approx(600 * info["input_cost_per_token"] + 400 * cache_read_rate)
assert response_completion_cost == pytest.approx(500 * info["output_cost_per_token"])