scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-27 06:13:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 72

fix(cost): price base_model deployments past rule-only cost map entries (#47497)

Browse source 
* fix(cost): price base_model deployments past rule-only cost map entries and warn when base_model has no rates

* fix(router): warn on unpriced base_model from add_deployment too and honour model_info prices

* refactor(cost): drop the unpriced base_model startup warning, keep the one-line ladder fix

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Kerry Lu 2026-10-20 09:26:38 -07:00 • committed by GitHub
parent dd22dc9132
commit 8d2bf426f5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 33 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/cost_calculator.py
View file

@ -1642,7 +1642,7 @@ def completion_cost(
*(((model, request_pricing_provider),) if model is not None else ()),
)
potential_model_names: Final = (
raw_candidates if explicit_pricing else _priced_candidates_before_unpriced_rules(raw_candidates)
raw_candidates if custom_pricing is True else _priced_candidates_before_unpriced_rules(raw_candidates)
)
for idx, (model, pricing_provider) in enumerate(potential_model_names):

32
tests/unit/test_cost_calculator.py
View file

@ -391,6 +391,38 @@ def test_completion_cost_bills_undated_azure_data_zone_base_model_at_its_dated_r
)
def test_completion_cost_prices_rule_only_base_model_from_the_response_model(
_local_model_cost_map: None,
_price_free_gpt_family_generalization: None,
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""LIT-9812: a deployment whose base_model is an undated name only a capability rule matches must not
stop the ladder at $0 when the response names a priced model"""
monkeypatch.setattr(
litellm,
"model_cost",
{
"azure/gpt-9.9-2026-01-01": {
"litellm_provider": "azure",
"mode": "chat",
"input_cost_per_token": 0.0000111,
"output_cost_per_token": 0.0000222,
}
},
)
usage: Final = Usage(prompt_tokens=17, completion_tokens=9, total_tokens=26)
response: Final = ModelResponse(model="gpt-9.9-2026-01-01", choices=[], usage=usage)
cost: Final = completion_cost(
completion_response=response,
model="azure/my-eu-deployment",
custom_llm_provider="azure",
base_model="azure/eu/gpt-9.9",
)
assert cost == pytest.approx(usage.prompt_tokens * 0.0000111 + usage.completion_tokens * 0.0000222)
def test_completion_cost_orders_candidates_without_extra_huggingface_config_requests(
_local_model_cost_map: None,
) -> None: