scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-13 08:52:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 174
litellm/tests/integration/cost_calculation
History
Exact
Kerry Lu 3daeb8daf2
fix(transcription): stop billing a FLAC with no sample count as 576 trillion seconds (#50842) 
* fix(transcription): treat libsndfile's unknown frame count as no duration

* refactor(transcription): inline the unknown frame count check

* fix(transcription): read the frame count once to keep the type gate flat

* test(transcription): annotate the new passthrough test's locals as Final

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-11-10 06:19:33 +00:00
..
bridge_cost_parity test(cost): cover custom deployment aliases, off-peak pricing, bridge usage shapes and duplicate spend rows (#46708) 2026-10-15 10:44:51 -07:00
cases fix(transcription): stop billing a FLAC with no sample count as 576 trillion seconds (#50842) 2026-11-10 06:19:33 +00:00
stream_parity test(cost): add BridgeCostParityTestCase with a gpt-6-sol /v1/messages to Responses pair (#46130) 2026-10-13 02:51:55 +00:00
assertions.py test(integration): assert the streamed usage.cost matches the spend row on every cost case (#46762) 2026-10-15 22:34:42 +00:00
catalog.py test(cost): run azure_ai claude bridge pairs, add anthropic usage speed and vertex gemini audio priority price (#47582) 2026-10-20 17:10:16 +00:00
conftest.py test(cost): cover custom deployment aliases, off-peak pricing, bridge usage shapes and duplicate spend rows (#46708) 2026-10-15 10:44:51 -07:00
cost_map.py test(integration): cover claude-fable-5-2 capability flags and prompt-cache pricing on Vertex AI and Bedrock Converse (#50742) 2026-11-09 23:26:40 +00:00
cost_tracking_case.py fix(transcription): stop billing a FLAC with no sample count as 576 trillion seconds (#50842) 2026-11-10 06:19:33 +00:00
test_base_model_cross_provider_spend.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_batch_realtime_cost.py test: update the spend tests that still expected the pre-ledger accounting queues (#50814) 2026-11-09 22:07:42 -08:00
test_bridged_previous_response_id_spend.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_cost_tracking.py fix(transcription): stop billing a FLAC with no sample count as 576 trillion seconds (#50842) 2026-11-10 06:19:33 +00:00
test_messages_bridged_stream_margin_discount.py fix(cost): keep upstream_usage_cost on the Responses stream logging copy so bridged /v1/messages rows price their tokens (#49365) 2026-10-31 09:52:22 -07:00
test_responses_websocket_guardrail_spend.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00