scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49

test(cost_tracking): expect cache reads without a map rate to estimate at the input rate

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-09-18 16:33:17 +00:00
parent 88d1eb3b35
commit af61d9247c
1 changed files with 7 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
tests/test_litellm/proxy/management_endpoints/test_cost_tracking_settings.py
View file

@ -975,9 +975,9 @@ class TestEstimateCostCacheAndReasoningTokens:
@pytest.mark.asyncio
async def test_a_model_without_cache_or_reasoning_prices_estimates_what_the_proxy_bills(self, monkeypatch):
"""The cost calculator bills cache reads of a cost-map model without cache prices at zero,
its cache writes at the input rate, and its reasoning tokens at the output rate. The estimate
reports those effective rates."""
"""The cost calculator bills cache reads and writes of a cost-map model without cache prices
at the input rate, and its reasoning tokens at the output rate. The estimate reports those
effective rates."""
monkeypatch.setitem(
litellm.model_cost,
A_MAPPED_MODEL,
@ -986,14 +986,12 @@ class TestEstimateCostCacheAndReasoningTokens:
response = await _estimate_with_cache_and_reasoning(None, model=A_MAPPED_MODEL)
assert response.cache_read_cost_per_request == 0.0
assert response.cache_read_cost_per_request == pytest.approx(CACHE_READ_TOKENS * 5e-6)
assert response.cache_creation_cost_per_request == pytest.approx(CACHE_CREATION_TOKENS * 5e-6)
assert response.reasoning_cost_per_request == pytest.approx(REASONING_TOKENS * 6e-6)
assert response.input_cost_per_request == pytest.approx((TEXT_INPUT_TOKENS + CACHE_CREATION_TOKENS) * 5e-6)
assert response.cost_per_request == pytest.approx(
(TEXT_INPUT_TOKENS + CACHE_CREATION_TOKENS) * 5e-6 + OUTPUT_TOKENS * 6e-6
)
assert response.cache_read_input_token_cost == 0.0
assert response.input_cost_per_request == pytest.approx(INPUT_TOKENS * 5e-6)
assert response.cost_per_request == pytest.approx(INPUT_TOKENS * 5e-6 + OUTPUT_TOKENS * 6e-6)
assert response.cache_read_input_token_cost == pytest.approx(5e-6)
assert response.cache_creation_input_token_cost == pytest.approx(5e-6)
assert response.output_cost_per_reasoning_token == pytest.approx(6e-6)