redshift 01c01fe8ad fix: bill PPQ.AI BYOK upstream_inference_cost + BYOK fee ...

PPQ.AI (BYOK) requests were billed at ~5% of their true cost because
_resolve_usd_cost fell through to usage.cost (a small BYOK routing fee)
instead of using cost_details.upstream_inference_cost (the real inference
cost). The proxy operator absorbed the inference cost.

The fix adds a BYOK-specific branch in _resolve_usd_cost: when is_byok is
true and cost_details.upstream_inference_cost is present, bill
upstream_inference_cost + byok_fee — what PPQ actually deducts from the
balance. Non-BYOK providers (e.g. OpenRouter) are unaffected because their
usage.cost already equals upstream_inference_cost.

Regression tests mirror the live glm-5.2-fast request from GitHub issue #615,
asserting the corrected billing (940,274 msats vs the old 45,202 msats — a
20.8× undercharge).

Closes #615

2026-07-16 17:01:55 +08:00

..

__init__.py

small fixes

2025-11-11 15:42:26 +01:00

cost_calculation.py

fix: bill PPQ.AI BYOK upstream_inference_cost + BYOK fee

2026-07-16 17:01:55 +08:00

helpers.py

better rate limit forwarding

2026-06-20 20:03:40 +02:00

lnurl.py

fix payout

2026-07-05 23:35:10 +02:00

models.py

refactor(payment): extract litellm_cost_entry lookup helper

2026-07-03 14:42:17 +02:00

price.py

optimize price fetching

2026-01-10 17:37:05 +08:00

usage.py

resolve review comments

2026-06-13 23:40:39 +02:00