scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Merge 02e1b6ad6c into 3beb02e512

Browse source
This commit is contained in:
IvanShang 2026-08-28 12:13:34 +08:00 • committed by GitHub
commit 7c04b334e2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 32 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
tests/test_litellm/test_cost_calculator.py
View file

@ -2436,6 +2436,38 @@ def test_completion_cost_extracts_service_tier_from_usage(_local_model_cost_map)
), f"Flex pricing should be ~50% of standard, got {flex_ratio:.2f}"
@pytest.mark.parametrize(
("requested_model", "served_model", "input_rate", "output_rate"),
(
("gpt-4o", "gpt-4o-2024-08-06", 4.25e-6, 17e-6),
("gpt-4o", "gpt-4o-2024-11-20", 4.25e-6, 17e-6),
("gpt-4o-mini", "gpt-4o-mini-2024-07-18", 0.25e-6, 1e-6),
("gpt-4.1", "gpt-4.1-2025-04-14", 3.5e-6, 14e-6),
("gpt-4.1-mini", "gpt-4.1-mini-2025-04-14", 0.7e-6, 2.8e-6),
),
)
def test_completion_cost_uses_priority_rates_for_served_openai_snapshot(
monkeypatch,
requested_model,
served_model,
input_rate,
output_rate,
):
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
usage = Usage(prompt_tokens=100, completion_tokens=50, total_tokens=150)
response = ModelResponse(usage=usage, model=served_model)
cost = completion_cost(
completion_response=response,
model=requested_model,
custom_llm_provider="openai",
optional_params={"service_tier": "priority"},
)
assert cost == pytest.approx(100 * input_rate + 50 * output_rate)
def test_completion_cost_service_tier_priority(_local_model_cost_map):
"""Test that service_tier extraction follows priority: optional_params > completion_response > usage."""
from litellm import completion_cost