scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 91

Merge pull request #42010 from BerriAI/litellm_cost_shard_responses_messages

Browse source 
test(integration): native responses and messages cost cases
This commit is contained in:
kerry-berri 2026-09-19 14:20:31 -07:00 • committed by GitHub
commit 8323bef0e3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 1153 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

63
tests/integration/contracts.json
View file

@ -1320,6 +1320,69 @@
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[us.anthropic.claude-opus-5-v1:0-stream_full_usage]": [
"quota_management.spend_tracking.scripted_wire.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_cache_read]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_reasoning]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_stream]": [
"quota_management.spend_tracking.scripted_wire.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_stream_cache_read]": [
"quota_management.spend_tracking.scripted_wire.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_incomplete]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_previous_response_id]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_web_search_medium]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.3-codex-responses_file_search]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_service_tier_flex]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[gpt-5.6-responses_service_tier_priority]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_input_text]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_cache_read]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_cache_write_5m]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_cache_write_1h]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_web_search]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_stream]": [
"quota_management.spend_tracking.scripted_wire.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_stream_cache_read]": [
"quota_management.spend_tracking.scripted_wire.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-sonnet-5-messages_tiered_input_above_200k]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[claude-haiku-4-5-messages_input_text]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[us.anthropic.claude-opus-5-v1:0-messages_input_text]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
],
"tests/integration/cost_calculation/test_cost_tracking.py::test_case_bills_expected_cost[anthropic.claude-sonnet-5-v1:0-messages_cache_read]": [
"quota_management.spend_tracking.cost_matrix.logs_cost"
]
},
"browser": {

2
tests/integration/cost_calculation/cost_tracking_case.py
View file

@ -172,7 +172,7 @@ class CostTrackingTestCase(BaseModel):
provider: Final = self.rates.litellm_provider
prefix: Final = (
"openai"
if provider == "openai" and self.rates.mode == "chat"
if provider == "openai" and (self.rates.mode == "chat" or self.endpoint == "/v1/responses")
else "openai/responses"
if provider == "openai"
else _PROVIDER_PREFIXES.get(provider)

1086
tests/integration/cost_calculation/cost_tracking_cases.json
View file

File diff suppressed because it is too large Load diff

4
tests/integration/cost_calculation/test_cost_tracking.py
View file

@ -42,7 +42,9 @@ def _assert_stream_has_no_error(response_text: str) -> None:
if payload == "[DONE]":
continue
parsed = JSON_OBJECT.validate_json(payload)
assert "error" not in parsed, f"stream carried an error event: {parsed}"
assert (
"error" not in parsed and parsed.get("type") not in {"error", "response.failed"}
), f"stream carried an error event: {parsed}"
@pytest.mark.parametrize("case", _CASES)