fix(STR-1654): price LLM usage from model config

docs/advanced/configuration.mdx

@@ -19,6 +19,22 @@ Configure Strix using environment variables or a config file.
   Custom API base URL. Also accepts `OPENAI_API_BASE`, `LITELLM_BASE_URL`, or `OLLAMA_API_BASE`.
 </ParamField>
 
+<ParamField path="STRIX_LLM_INPUT_COST_PER_MTOK" type="number">
+  Price per 1M input tokens in USD for `STRIX_LLM`. Use it for gateway or self-hosted model ids that LiteLLM can't price.
+</ParamField>
+
+<ParamField path="STRIX_LLM_OUTPUT_COST_PER_MTOK" type="number">
+  Price per 1M output tokens in USD for `STRIX_LLM`.
+</ParamField>
+
+<ParamField path="STRIX_LLM_CACHED_INPUT_COST_PER_MTOK" type="number">
+  Price per 1M cached input tokens in USD for `STRIX_LLM`. If unset, cached tokens use the input price.
+</ParamField>
+
+<Note>
+  Setting any of these prices replaces the provider-reported and LiteLLM cost for `STRIX_LLM` in reports and `--max-budget`. An unset input or output price counts as `0`, so set both. A separate `STRIX_DEDUPE_MODEL` keeps its LiteLLM price.
+</Note>
+
 <ParamField path="STRIX_API_TYPE" type="string">
   Select the OpenAI API path for the model: `responses` or `chat_completions`.
   By default the model decides: Responses when LiteLLM's model catalog lists

strix/config/settings.py

@@ -61,6 +61,15 @@ class LlmSettings(BaseSettings):
         repr=False,
     )
     reasoning_effort: ReasoningEffort = Field(default="high", alias="STRIX_REASONING_EFFORT")
+    input_cost_per_mtok: float | None = Field(
+        default=None, ge=0, allow_inf_nan=False, alias="STRIX_LLM_INPUT_COST_PER_MTOK"
+    )
+    output_cost_per_mtok: float | None = Field(
+        default=None, ge=0, allow_inf_nan=False, alias="STRIX_LLM_OUTPUT_COST_PER_MTOK"
+    )
+    cached_input_cost_per_mtok: float | None = Field(
+        default=None, ge=0, allow_inf_nan=False, alias="STRIX_LLM_CACHED_INPUT_COST_PER_MTOK"
+    )
     force_required_tool_choice: bool = Field(
         default=False,
         alias="STRIX_FORCE_REQUIRED_TOOL_CHOICE",

strix/report/usage.py

@@ -8,11 +8,38 @@
 from agents.usage import Usage, deserialize_usage, serialize_usage
 from pydantic import BaseModel, TypeAdapter, ValidationError
 
+from strix.config.loader import load_settings
 from strix.report.pricing import resolve_litellm_model
 
 
 logger = logging.getLogger(__name__)
 
+Prices = tuple[float | None, float | None, float | None]
+
+
+def _configured_prices() -> tuple[str | None, Prices | None]:
+    llm = load_settings().llm
+    prices = (llm.input_cost_per_mtok, llm.output_cost_per_mtok, llm.cached_input_cost_per_mtok)
+    if all(price is None for price in prices):
+        return None, None
+    return (llm.model or "").strip() or None, prices
+
+
+def _configured_usage_cost(usage: Usage, prices: Prices) -> float:
+    input_rate, output_rate, cached_rate = prices
+    input_tokens = max(0, _int_or_zero(getattr(usage, "input_tokens", 0)))
+    cached_details = getattr(usage, "input_tokens_details", None)
+    cached_tokens = max(0, _int_or_zero(getattr(cached_details, "cached_tokens", 0)))
+    cached_tokens = min(cached_tokens, input_tokens)
+    output_tokens = max(0, _int_or_zero(getattr(usage, "output_tokens", 0)))
+    billable_input = input_tokens - cached_tokens
+    cost = (
+        billable_input * (input_rate or 0)
+        + cached_tokens * (cached_rate if cached_rate is not None else input_rate or 0)
+        + output_tokens * (output_rate or 0)
+    ) / 1_000_000
+    return _round_cost(cost)
+
 
 class ProviderUsage(BaseModel):
     """Running totals for one upstream provider OpenRouter routed calls to."""
@@ -37,6 +64,7 @@ def __init__(self) -> None:
         self._total_usage = Usage()
         self._agent_usage: dict[str, Usage] = {}
         self._agent_metadata: dict[str, dict[str, str]] = {}
+        self._agent_estimated_cost: dict[str, float] = {}
         self._observed_cost = 0.0
         self._estimated_cost = 0.0
         self._has_observed_cost = False
@@ -73,6 +101,9 @@ def record(
             estimated = _estimate_litellm_cost(usage, model)
             if estimated:
                 self._estimated_cost += estimated
+                self._agent_estimated_cost[normalized_agent_id] = (
+                    self._agent_estimated_cost.get(normalized_agent_id, 0.0) + estimated
+                )
 
         return True
 
@@ -114,11 +145,23 @@ def record_provider(
     def total_cost(self) -> float:
         if self.zero_cost:
             return 0.0
+        model, prices = _configured_prices()
+        if prices is not None:
+            return _round_cost(
+                sum(self._configured_agent_cost(aid, model, prices) for aid in self._agent_usage)
+            )
         return _round_cost(self._observed_cost if self._has_observed_cost else self._estimated_cost)
 
+    def _configured_agent_cost(self, agent_id: str, model: str | None, prices: Prices) -> float:
+        if self._agent_metadata.get(agent_id, {}).get("model") == model:
+            return _configured_usage_cost(self._agent_usage[agent_id], prices)
+        return self._agent_estimated_cost.get(agent_id, 0.0)
+
     def to_record(self) -> dict[str, Any]:
         record = serialize_usage(self._total_usage)
-        record["cost"] = self.total_cost
+        model, prices = _configured_prices()
+        total_cost = self.total_cost
+        record["cost"] = total_cost
         record["providers"] = {name: tally.model_dump() for name, tally in self._providers.items()}
         record["agents"] = []
 
@@ -128,7 +171,11 @@ def to_record(self) -> dict[str, Any]:
             usage = self._agent_usage[agent_id]
             metadata = self._agent_metadata.get(agent_id, {})
             agent_cost = (
-                self.total_cost * (agent_tokens[agent_id] / total_tokens) if total_tokens else 0.0
+                self._configured_agent_cost(agent_id, model, prices)
+                if prices is not None and not self.zero_cost
+                else total_cost * (agent_tokens[agent_id] / total_tokens)
+                if total_tokens
+                else 0.0
             )
 
             agent_record = serialize_usage(usage)
@@ -148,6 +195,7 @@ def hydrate(self, raw_usage: Any) -> None:
         self._total_usage = Usage()
         self._agent_usage.clear()
         self._agent_metadata.clear()
+        self._agent_estimated_cost.clear()
         self._observed_cost = 0.0
         self._estimated_cost = 0.0
         self._has_observed_cost = False
@@ -183,6 +231,7 @@ def hydrate(self, raw_usage: Any) -> None:
                 logger.exception("Failed to hydrate llm_usage for agent %s", agent_id)
                 self._agent_usage[agent_id] = Usage()
 
+            self._agent_estimated_cost[agent_id] = _float_or_zero(raw_agent.get("cost"))
             metadata: dict[str, str] = {}
             agent_name = raw_agent.get("agent_name")
             model = raw_agent.get("model")

tests/test_hooks.py

@@ -2,11 +2,14 @@
 
 from __future__ import annotations
 
-from typing import Any
+from types import SimpleNamespace
+from typing import TYPE_CHECKING, Any
 from unittest.mock import MagicMock, patch
 
 import pytest
+from agents.usage import Usage
 
+from strix.config import loader
 from strix.core.agents import AgentCoordinator
 from strix.core.hooks import (
     BudgetExceededError,
@@ -15,6 +18,11 @@
     SubagentBudgetReservedError,
     recomputed_budget_flags,
 )
+from strix.report.usage import LLMUsageLedger
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
 
 
 def _make_hooks(max_budget: float | None) -> ReportUsageHooks:
@@ -85,6 +93,38 @@ async def test_over_budget_raises() -> None:
         await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
 
 
+@pytest.mark.asyncio
+async def test_manual_rates_make_unpriced_model_trip_budget(
+    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+) -> None:
+    monkeypatch.setenv("STRIX_LLM", "test-model")
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "10")
+    monkeypatch.delenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", raising=False)
+    monkeypatch.delenv("STRIX_LLM_CACHED_INPUT_COST_PER_MTOK", raising=False)
+    monkeypatch.setattr(loader, "_override", tmp_path / "missing.json")
+    monkeypatch.setattr(loader, "_cached", None)
+    usage = Usage()
+    usage.requests = 1
+    usage.input_tokens = 1000
+    usage.total_tokens = 1000
+    ledger = LLMUsageLedger()
+
+    class ReportState:
+        def record_sdk_usage(self, **kwargs: Any) -> None:
+            ledger.record(**kwargs)
+
+        def get_total_llm_cost(self) -> float:
+            return ledger.total_cost
+
+    hooks = _make_hooks(0.005)
+    response: Any = SimpleNamespace(usage=usage)
+    with (
+        patch("strix.core.hooks.get_global_report_state", return_value=ReportState()),
+        pytest.raises(BudgetExceededError),
+    ):
+        await hooks.on_llm_end(_make_context(), MagicMock(), response)
+
+
 @pytest.mark.asyncio
 async def test_budget_check_uses_live_cost_accessor() -> None:
     # The check must read the live ledger, not the persisted run-record snapshot,

tests/test_pricing.py

@@ -1,14 +1,50 @@
 from __future__ import annotations
 
+import json
+from typing import TYPE_CHECKING
 from unittest.mock import patch
 
 import litellm
+import pytest
 from agents.usage import Usage
+from pydantic import ValidationError
 
+from strix.config import loader
+from strix.config.settings import LlmSettings
 from strix.report.pricing import resolve_litellm_model
 from strix.report.usage import LLMUsageLedger
 
 
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+PRICE_ENV = (
+    "STRIX_LLM_INPUT_COST_PER_MTOK",
+    "STRIX_LLM_OUTPUT_COST_PER_MTOK",
+    "STRIX_LLM_CACHED_INPUT_COST_PER_MTOK",
+)
+
+
+@pytest.fixture(autouse=True)
+def _isolated_settings(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
+    for name in PRICE_ENV:
+        monkeypatch.delenv(name, raising=False)
+    monkeypatch.setenv("STRIX_LLM", "gateway/unpriced-model")
+    monkeypatch.setattr(loader, "_override", tmp_path / "missing.json")
+    monkeypatch.setattr(loader, "_cached", None)
+
+
+def _usage(input_tokens: int, output_tokens: int = 0, cached_tokens: int = 0) -> Usage:
+    usage = Usage()
+    usage.requests = 1
+    usage.input_tokens = input_tokens
+    usage.output_tokens = output_tokens
+    usage.total_tokens = input_tokens + output_tokens
+    usage.input_tokens_details.cached_tokens = cached_tokens
+    return usage
+
+
 def test_resolves_common_bare_model_names() -> None:
     resolve_litellm_model.cache_clear()
     assert resolve_litellm_model("deepseek-v4-flash") == "deepseek/deepseek-v4-flash"
@@ -60,6 +96,112 @@ def test_ledger_prefers_observed_cost_over_estimate() -> None:
     assert ledger.total_cost == 0.17
 
 
+def test_unpriced_model_without_manual_rates_costs_zero() -> None:
+    ledger = LLMUsageLedger()
+
+    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
+
+    assert ledger.total_cost == 0.0
+
+
+def test_manual_rates_price_usage_and_override_observed_cost(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "2")
+    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "8")
+    ledger = LLMUsageLedger()
+
+    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
+    ledger.record_observed_cost(0.17)
+
+    assert ledger.total_cost == 0.0036
+    assert ledger.to_record()["agents"][0]["cost"] == 0.0036
+
+
+def test_manual_rates_from_config_file(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    path = tmp_path / "config.json"
+    path.write_text(
+        json.dumps(
+            {
+                "env": {
+                    "STRIX_LLM_INPUT_COST_PER_MTOK": "2",
+                    "STRIX_LLM_OUTPUT_COST_PER_MTOK": "8",
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+    monkeypatch.setattr(loader, "_override", path)
+    ledger = LLMUsageLedger()
+
+    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
+
+    assert ledger.total_cost == 0.0036
+
+
+def test_manual_rates_only_price_the_configured_model(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "2")
+    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "8")
+    ledger = LLMUsageLedger()
+
+    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
+    with patch("litellm.completion_cost", return_value=0.42):
+        ledger.record(agent_id="dedupe", usage=_usage(500, 50), model="deepseek/deepseek-v4-flash")
+    record = ledger.to_record()
+
+    assert ledger.total_cost == 0.4236
+    assert {agent["agent_id"]: agent["cost"] for agent in record["agents"]} == {
+        "a": 0.0036,
+        "dedupe": 0.42,
+    }
+
+
+def test_cached_tokens_fall_back_to_input_rate(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "5")
+    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "7")
+    ledger = LLMUsageLedger()
+
+    ledger.record(
+        agent_id="a", usage=_usage(10, 1, cached_tokens=2), model="gateway/unpriced-model"
+    )
+
+    assert ledger.total_cost == 0.000057
+
+
+def test_hydrated_usage_uses_configured_rates_not_persisted_cost(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "2")
+    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "8")
+    original = LLMUsageLedger()
+    original.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
+    persisted = original.to_record()
+    persisted["cost"] = 42.0
+    persisted["agents"][0]["cost"] = 42.0
+    hydrated = LLMUsageLedger()
+
+    hydrated.hydrate(persisted)
+
+    assert hydrated.total_cost == 0.0036
+
+
+@pytest.mark.parametrize("value", ["invalid", "-1", "nan", "inf"])
+def test_invalid_manual_rate_is_rejected(value: str, monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", value)
+    with pytest.raises(ValidationError):
+        LlmSettings()
+
+
+def test_zero_cost_overrides_manual_rates(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "10")
+    ledger = LLMUsageLedger()
+    ledger.zero_cost = True
+
+    ledger.record(agent_id="a", usage=_usage(1000), model="gateway/unpriced-model")
+
+    assert ledger.total_cost == 0.0
+
+
 def test_hydrated_estimate_continues_accumulating_new_estimates() -> None:
     usage = Usage()
     usage.requests = 1