fix(accounting): store zero savings when caller data makes them uncomputable

A huge caller-supplied tokens_saved overflowed the savings math inside
build_accounting_payload, which dropped the request's charge in ledger mode.
Savings that cannot be computed are now recorded as zero and the charge lands.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

litellm/accounting/snapshot.py

@@ -4,10 +4,11 @@ from typing import TYPE_CHECKING, Final
 
 from pydantic import TypeAdapter, ValidationError
 
+from litellm._logging import verbose_proxy_logger
 from litellm.litellm_core_utils.safe_json_dumps import safe_json_structure
 from litellm.proxy._types import SpendLogsPayload
 from litellm.proxy.spend_tracking.compression_savings import extract_compression_saved_tokens
-from litellm.proxy.spend_tracking.savings import compute_savings_spend, marks_gateway_injection
+from litellm.proxy.spend_tracking.savings import SavingsSpend, compute_savings_spend, marks_gateway_injection
 
 if TYPE_CHECKING:
     from litellm.router import Router
@@ -66,20 +67,7 @@ def build_accounting_payload(
     router: "Callable[[], Router | None]",
 ) -> Mapping[str, object]:
     metadata: Final = _FIELDS.validate_json(payload["metadata"])
-    savings: Final = compute_savings_spend(
-        model=payload["model"],
-        custom_llm_provider=payload["custom_llm_provider"],
-        compression_saved_tokens=extract_compression_saved_tokens(metadata),
-        gateway_injected_cache=marks_gateway_injection(metadata, payload["model_id"]),
-        routing_decision=_mapping(metadata.get("routing_decision")),
-        model_id=payload["model_id"],
-        llm_router=router,
-        usage_object=_mapping(metadata.get("usage_object")),
-        cost_breakdown=_mapping(metadata.get("cost_breakdown")),
-        recorded_autorouter_savings=metadata.get("autorouter_savings"),
-        recorded_autorouter_savings_estimate=_mapping(metadata.get("autorouter_savings_estimate")),
-        billed_at=payload["endTime"],
-    )
+    savings: Final = _savings_or_zero(payload, metadata, router)
     accounting_metadata: Final = {
         **{key: _accounting_metadata_field(key, value) for key, value in metadata.items() if key in _METADATA_FIELDS},
         "accounting_entities": entities,
@@ -102,6 +90,39 @@ def build_accounting_payload(
     )
 
 
+def _savings_or_zero(
+    payload: SpendLogsPayload, metadata: Mapping[str, object], router: "Callable[[], Router | None]"
+) -> SavingsSpend:
+    """Savings are analytics computed from caller-supplied counts, so one that cannot be computed is stored as zero
+    rather than losing the charge it rides with."""
+    try:
+        return _savings(payload, metadata, router)
+    except (ArithmeticError, ValueError, TypeError) as error:
+        verbose_proxy_logger.warning(
+            "Recording zero savings for request_id=%s, savings could not be computed: %s", payload["request_id"], error
+        )
+        return SavingsSpend(compression=0.0, prompt_caching=0.0)
+
+
+def _savings(
+    payload: SpendLogsPayload, metadata: Mapping[str, object], router: "Callable[[], Router | None]"
+) -> SavingsSpend:
+    return compute_savings_spend(
+        model=payload["model"],
+        custom_llm_provider=payload["custom_llm_provider"],
+        compression_saved_tokens=extract_compression_saved_tokens(metadata),
+        gateway_injected_cache=marks_gateway_injection(metadata, payload["model_id"]),
+        routing_decision=_mapping(metadata.get("routing_decision")),
+        model_id=payload["model_id"],
+        llm_router=router,
+        usage_object=_mapping(metadata.get("usage_object")),
+        cost_breakdown=_mapping(metadata.get("cost_breakdown")),
+        recorded_autorouter_savings=metadata.get("autorouter_savings"),
+        recorded_autorouter_savings_estimate=_mapping(metadata.get("autorouter_savings_estimate")),
+        billed_at=payload["endTime"],
+    )
+
+
 _GUARDRAIL_ENTRIES: Final = TypeAdapter(tuple[dict[str, object], ...])
 _GUARDRAIL_METADATA_FIELDS: Final = frozenset({"guardrail_information", "standard_logging_guardrail_information"})
 _GUARDRAIL_ACCOUNTING_FIELDS: Final = frozenset(

tests/unit/accounting/test_projection.py

@@ -519,3 +519,39 @@ def test_stored_payload_keeps_guardrail_billing_but_not_guardrail_content() -> N
     assert [dict(item.increments) for item in usage_rows] == [{"units": 1, "cost": 0.25, "untracked_units": 0}]
     daily_user: Final = next(item for item in project(restored) if item.table == "LiteLLM_DailyUserSpend")
     assert dict(daily_user.increments)["compression_saved_tokens"] == 7
+
+
+def test_caller_supplied_savings_that_cannot_be_computed_never_drop_the_charge(monkeypatch: pytest.MonkeyPatch) -> None:
+    import litellm
+
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "savings-overflow-test",
+        {"input_cost_per_token": 0.002, "output_cost_per_token": 0.004, "litellm_provider": "openai", "mode": "chat"},
+    )
+    payload: Final[SpendLogsPayload] = {
+        **get_logging_payload(
+            kwargs={
+                "model": "savings-overflow-test",
+                "custom_llm_provider": "openai",
+                "call_type": "acompletion",
+                "litellm_call_id": "overflow-request",
+                "litellm_params": {"metadata": {"user_api_key": "key"}},
+            },
+            response_obj=ModelResponse(
+                id="overflow-request", model="savings-overflow-test", usage=Usage(prompt_tokens=10, completion_tokens=5)
+            ),
+            start_time=_NOW,
+            end_time=_NOW,
+        ),
+        "spend": 0.5,
+        "metadata": json.dumps({"compression_savings": {"tokens_saved": 10**400}}),
+    }
+    accounting: Final = build_accounting_payload(
+        payload, entities={"api_key": "key"}, model_access_groups=(), windows=(), router=lambda: None
+    )
+    restored: Final = _FIELDS.validate_json(json.dumps(accounting, default=str))
+    assert dict(restored["metadata"])["accounting_savings"]["compression"] == 0.0
+    assert [dict(item.increments)["spend"] for item in project(restored) if item.table == "LiteLLM_VerificationToken"] == [
+        0.5
+    ]