diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
index 2177e483a1b..f119689e6ec 100644
--- a/ARCHITECTURE.md
+++ b/ARCHITECTURE.md
@@ -239,6 +239,8 @@ graph LR
 7. `DBSpendUpdateWriter.update_database()` queues spend increments to Redis
 8. Background job `update_spend` flushes queued spend to PostgreSQL every 60s
 
+Cost lookup falls back to the response model when the provider-reported name cannot be priced. Explicitly registered zero rates remain zero, and custom deployment pricing or an explicit `base_model` retain precedence
+
 ### Data Access Layer (Models & Repositories)
 
 Database entities and the operations on them live in two packages at the root of `litellm/` so both the gateway (`proxy/`) and the SDK can use them without importing proxy internals:
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 89a1b544b82..0ed63a1e7f9 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -94,6 +94,8 @@ Add your tests to the [`tests/unit/` directory](https://github.com/BerriAI/litel
 - **Only add mocked tests** - no real LLM API calls in this directory
 - For integration tests with real APIs, use the appropriate test directories
 
+Tests that call `litellm.register_model` or change `litellm.model_cost` should use the `local_model_cost_map` fixture from `tests/unit/conftest.py`. It provides a fresh catalog and restores the previous map, so pricing and capability overrides cannot leak into later tests
+
 ### File Naming Convention
 
 The `tests/unit/` directory follows the same structure as `litellm/`:
diff --git a/tests/unit/test_cost_calculator.py b/tests/unit/test_cost_calculator.py
index 27b25c1f98e..84f6dab9eff 100644
--- a/tests/unit/test_cost_calculator.py
+++ b/tests/unit/test_cost_calculator.py
@@ -6810,6 +6810,73 @@ def test_completion_cost_bills_base_when_gemini_serves_on_demand(
     assert cost == pytest.approx(100 * 0.001 + 50 * 0.002)
 
 
+def test_an_unpriced_provider_slug_does_not_bill_the_turn_at_zero(
+    _local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    response_model: Final = "anthropic/claude-test-42161-response"
+    reported_model: Final = "claude-test-42161-unmapped"
+    monkeypatch.delitem(litellm.model_cost, reported_model, raising=False)
+    monkeypatch.delitem(litellm.model_cost, f"anthropic/{reported_model}", raising=False)
+    monkeypatch.setitem(
+        litellm.model_cost,
+        response_model,
+        {
+            "input_cost_per_token": 0.001,
+            "output_cost_per_token": 0.002,
+            "litellm_provider": "anthropic",
+            "mode": "chat",
+        },
+    )
+    response: Final = ModelResponse(
+        model=response_model,
+        choices=[],
+        usage=Usage(prompt_tokens=38, completion_tokens=24, total_tokens=62),
+    )
+    response._hidden_params["provider_response_model"] = reported_model
+
+    cost: Final = completion_cost(completion_response=response, custom_llm_provider="anthropic")
+
+    assert cost == pytest.approx(38 * 0.001 + 24 * 0.002)
+
+
+@pytest.mark.parametrize("reported_rate", (0.0, 0.01))
+def test_a_priced_provider_slug_still_decides_the_rate(
+    _local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch, reported_rate: float
+) -> None:
+    response_model: Final = "anthropic/claude-test-42161-response"
+    reported_model: Final = "claude-test-42161-reported"
+    monkeypatch.setitem(
+        litellm.model_cost,
+        response_model,
+        {
+            "input_cost_per_token": 0.001,
+            "output_cost_per_token": 0.002,
+            "litellm_provider": "anthropic",
+            "mode": "chat",
+        },
+    )
+    monkeypatch.setitem(
+        litellm.model_cost,
+        f"anthropic/{reported_model}",
+        {
+            "input_cost_per_token": reported_rate,
+            "output_cost_per_token": reported_rate * 2,
+            "litellm_provider": "anthropic",
+            "mode": "chat",
+        },
+    )
+    response: Final = ModelResponse(
+        model=response_model,
+        choices=[],
+        usage=Usage(prompt_tokens=38, completion_tokens=24, total_tokens=62),
+    )
+    response._hidden_params["provider_response_model"] = reported_model
+
+    cost: Final = completion_cost(completion_response=response, custom_llm_provider="anthropic")
+
+    assert cost == pytest.approx(38 * reported_rate + 24 * reported_rate * 2)
+
+
 def test_custom_pricing_as_completion_cost_param():
     from litellm import Choices, Message, ModelResponse
     from litellm.utils import Usage