Skip to content

fix(utils): prefer regional inference-profile price over stripped base price #30331

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Ewertonslv wants to merge 1 commit into from
+21 −6
Closed

fix(utils): prefer regional inference-profile price over stripped base price #30331

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions litellm/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5902,9 +5902,9 @@ def _get_model_info_helper( # noqa: PLR0915
Check if: (in order of specificity)
1. 'custom_llm_provider/model' in litellm.model_cost. Checks "groq/llama3-8b-8192" if model="llama3-8b-8192" and custom_llm_provider="groq"
2. 'model' in litellm.model_cost. Checks "gemini-1.5-pro-002" in litellm.model_cost if model="gemini-1.5-pro-002" and custom_llm_provider=None
3. 'combined_stripped_model_name' in litellm.model_cost. Checks if 'gemini/gemini-1.5-flash' in model map, if 'gemini/gemini-1.5-flash-001' given.
4. 'stripped_model_name' in litellm.model_cost. Checks if 'ft:gpt-3.5-turbo' in model map, if 'ft:gpt-3.5-turbo:my-org:custom_suffix:id' given.
5. 'split_model' in litellm.model_cost. Checks "llama3-8b-8192" in litellm.model_cost if model="groq/llama3-8b-8192"
3. 'split_model' in litellm.model_cost. Checks "au.anthropic.claude-3" in litellm.model_cost if model="bedrock/au.anthropic.claude-3". Tried before the stripped names so a regional inference profile keeps its region-specific price instead of falling back to the stripped base price.
4. 'combined_stripped_model_name' in litellm.model_cost. Checks if 'gemini/gemini-1.5-flash' in model map, if 'gemini/gemini-1.5-flash-001' given.
5. 'stripped_model_name' in litellm.model_cost. Checks if 'ft:gpt-3.5-turbo' in model map, if 'ft:gpt-3.5-turbo:my-org:custom_suffix:id' given.
"""

_model_info: Optional[Dict[str, Any]] = None
Expand All @@ -5931,7 +5931,7 @@ def _get_model_info_helper( # noqa: PLR0915
):
_model_info = None
if _model_info is None:
_matched_key = _get_model_cost_key(combined_stripped_model_name)
_matched_key = _get_model_cost_key(split_model)
if _matched_key is not None:
key = _matched_key
_model_info = _get_model_info_from_model_cost(key=cast(str, key))
Expand All @@ -5941,7 +5941,7 @@ def _get_model_info_helper( # noqa: PLR0915
):
_model_info = None
if _model_info is None:
_matched_key = _get_model_cost_key(stripped_model_name)
_matched_key = _get_model_cost_key(combined_stripped_model_name)
if _matched_key is not None:
key = _matched_key
_model_info = _get_model_info_from_model_cost(key=cast(str, key))
Expand All @@ -5951,7 +5951,7 @@ def _get_model_info_helper( # noqa: PLR0915
):
_model_info = None
if _model_info is None:
_matched_key = _get_model_cost_key(split_model)
_matched_key = _get_model_cost_key(stripped_model_name)
if _matched_key is not None:
key = _matched_key
_model_info = _get_model_info_from_model_cost(key=cast(str, key))
Expand Down
15 changes: 15 additions & 0 deletions tests/local_testing/test_get_model_info.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,21 @@ def test_get_model_info_bedrock_region():
assert info["litellm_provider"] == "bedrock_converse"


def test_get_model_info_bedrock_region_uses_regional_price():
"""A regional inference-profile model keeps its region-specific price instead
of falling back to the stripped base-model price (issue #27612)."""
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
regional_key = "au.anthropic.claude-sonnet-4-5-20250929-v1:0"
info = litellm.get_model_info(model="bedrock/" + regional_key)
print("info", info)
assert info["key"] == regional_key
assert (
info["input_cost_per_token"]
== litellm.model_cost[regional_key]["input_cost_per_token"]
)


@pytest.mark.parametrize(
"model",
[
Expand Down
Loading