Merge pull request #616 from Routstr/fix/ppq-upstream-inference-cost

fix: bill PPQ.AI BYOK upstream_inference_cost + BYOK fee

routstr/payment/cost_calculation.py

@@ -264,7 +264,17 @@ def _coerce_usd(value: object) -> float:
 def _resolve_usd_cost(usage_data: dict, response_data: dict) -> float:
     """Resolve USD cost with clear priority order.
 
-    Priority: cost_details.total_cost → total_cost → cost (in both usage and response).
+    Priority:
+
+    1. ``cost_details.total_cost``
+    2. ``cost_details.upstream_inference_cost`` (BYOK — see below)
+    3. ``total_cost`` → ``cost`` (in both usage and response)
+
+    **BYOK path (PPQ.AI):** when ``is_byok`` is true the ``usage.cost`` field
+    is only a small (~5 %) routing fee, not the inference cost.  The real cost
+    lives in ``cost_details.upstream_inference_cost`` and the provider's
+    balance is debited by ``upstream_inference_cost + byok_fee``.  Billing just
+    the fee under-charges by ~20×.
     """
     cost_details = usage_data.get("cost_details")
     if isinstance(cost_details, dict):
@@ -272,6 +282,18 @@ def _resolve_usd_cost(usage_data: dict, response_data: dict) -> float:
         if cost > 0:
             return cost
 
+        # PPQ.AI BYOK: upstream_inference_cost is the real inference cost;
+        # usage.cost is only a ~5 % BYOK routing fee.  Bill the sum — what PPQ
+        # actually deducts from the balance.  For non-BYOK providers (e.g.
+        # OpenRouter) usage.cost already equals upstream_inference_cost, so we
+        # fall through to the normal ``cost`` lookup below.
+        upstream_cost = _coerce_usd(
+            cost_details.get("upstream_inference_cost")
+        )
+        if upstream_cost > 0 and usage_data.get("is_byok"):
+            byok_fee = _coerce_usd(usage_data.get("cost"))
+            return upstream_cost + byok_fee
+
     for source in [usage_data, response_data]:
         if not isinstance(source, dict):
             continue

tests/unit/test_cost_calculation_caching.py

@@ -532,6 +532,72 @@ async def test_openrouter_upstream_inference_cost_components_are_used() -> None:
     assert result.input_msats + result.output_msats == result.total_msats == 4471
 
 
+# ============================================================================
+# PPQ.AI BYOK: upstream_inference_cost + BYOK fee billing
+#
+# PPQ.AI (bring-your-own-key) returns a small ~5 % BYOK routing fee in
+# ``usage.cost`` and the real inference cost in
+# ``cost_details.upstream_inference_cost``.  The old code billed only the fee,
+# under-charging by ~20×.  The fix bills ``upstream_inference_cost + byok_fee``
+# — what PPQ actually deducts from the balance.
+# Payload numbers are from a live ``glm-5.2-fast`` request (GitHub issue #615).
+# ============================================================================
+@pytest.mark.asyncio
+async def test_ppq_byok_bills_upstream_inference_cost_plus_fee() -> None:
+    """PPQ.AI BYOK must bill upstream_inference_cost + byok_fee, not just the
+    fee.  Mirrors the live request from GitHub issue #615."""
+    response = {
+        "model": "glm-5.2-fast",
+        "usage": {
+            "prompt_tokens": 164371,  # includes 159301 cached
+            "completion_tokens": 99,
+            "cost": 0.002260057305,  # ~5% BYOK routing fee
+            "is_byok": True,
+            "prompt_tokens_details": {"cached_tokens": 159301},
+            "cost_details": {
+                "upstream_inference_cost": 0.04475361,
+                "upstream_inference_prompt_cost": 0.04410021,
+                "upstream_inference_completions_cost": 0.0006534,
+            },
+        },
+    }
+    result = await calculate_cost(response, max_cost=100000)
+
+    assert isinstance(result, CostData)
+    # The fix bills upstream_inference_cost + byok_fee (~0.047 USD → ~940k
+    # msats), not the fee alone (~0.0023 USD → ~45k msats).  ~20× correction.
+    assert result.total_msats == 940274
+    assert result.input_msats + result.output_msats == result.total_msats
+    assert result.input_msats == 926546
+    assert result.output_msats == 13728
+    assert result.total_usd == pytest.approx(0.047013667305)
+    # Token normalisation (OpenAI dialect: cached included in prompt_tokens)
+    assert result.input_tokens == 5070  # 164371 - 159301
+    assert result.cache_read_input_tokens == 159301
+    assert result.output_tokens == 99
+
+
+@pytest.mark.asyncio
+async def test_ppq_byok_fee_only_would_undercharge() -> None:
+    """Sanity check: billing only usage.cost (the BYOK fee) under-charges by
+    ~20×.  This documents the regression the fix prevents."""
+    response = {
+        "model": "glm-5.2-fast",
+        "usage": {
+            "prompt_tokens": 164371,
+            "completion_tokens": 99,
+            "cost": 0.002260057305,  # BYOK fee only — no upstream_inference_cost
+            "is_byok": True,
+            "prompt_tokens_details": {"cached_tokens": 159301},
+        },
+    }
+    result = await calculate_cost(response, max_cost=100000)
+
+    assert isinstance(result, CostData)
+    # Without upstream_inference_cost, only the fee is billed — the old bug.
+    assert result.total_msats == 45202
+
+
 # ============================================================================
 # Test 13: Missing Usage Block
 # ============================================================================