scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Refactor model cost calculation for multimodal embedding

Browse source
This commit is contained in:
Praveen11558 2026-03-23 23:26:32 +05:30 • committed by GitHub
parent d3de061d6f
commit 3582b3af1d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -1397,6 +1397,10 @@ def test_image_count_billing_does_not_fill_prompt_token_gap():
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
# multimodalembedding@001 has non-zero input_cost_per_image (0.0001) and
# input_cost_per_token (8e-07), making the image billing assertion non-trivial.
model = "multimodalembedding@001"
usage = Usage(
prompt_tokens=10000,
completion_tokens=200,
@ -1408,12 +1412,12 @@ def test_image_count_billing_does_not_fill_prompt_token_gap():
)
prompt_cost, completion_cost = generic_cost_per_token(
model="gemini-2.0-flash-001",
model=model,
usage=usage,
custom_llm_provider="vertex_ai",
)
model_info = litellm.model_cost["gemini-2.0-flash-001"]
model_info = litellm.model_cost[model]
input_cost_per_token = model_info["input_cost_per_token"]
output_cost_per_token = model_info["output_cost_per_token"]
input_cost_per_image = model_info.get("input_cost_per_image", 0) or 0
@ -1431,7 +1435,6 @@ def test_image_count_billing_does_not_fill_prompt_token_gap():
)
assert completion_cost == pytest.approx(expected_completion_cost)
def test_character_count_billing_does_not_fill_prompt_token_gap():
"""
Regression: when character_count pricing is active, gaps between