fix: resolve base_model in /cost/estimate for Azure custom deployments (#22724)

The _resolve_model_for_cost_lookup function was only checking
litellm_params.model when resolving model names from the router.
For Azure custom deployment names (e.g. azure/openai/gpt-5.3-codex),
this deployment name doesn't exist in the model cost map, so cost
returned /bin/zsh.

Now checks model_info.base_model and litellm_params.base_model first,
falling back to litellm_params.model only if no base_model is set.
This matches how the router resolves base_model everywhere else.

litellm/proxy/management_endpoints/cost_tracking_settings.py

@@ -54,16 +54,27 @@ def _resolve_model_for_cost_lookup(model: str) -> Tuple[str, Optional[str]]:
             deployments = llm_router.get_model_list(model_name=model)
 
             if deployments and len(deployments) > 0:
-                # Get the first deployment's litellm model
                 first_deployment = deployments[0]
                 litellm_params = first_deployment.get("litellm_params", {})
+                model_info = first_deployment.get("model_info", {})
+
+                # Check base_model first (needed for Azure custom deployment names)
+                base_model = model_info.get("base_model") or litellm_params.get(
+                    "base_model"
+                )
+                if base_model:
+                    verbose_proxy_logger.debug(
+                        f"Resolved model '{model}' to base_model '{base_model}' from router"
+                    )
+                    custom_llm_provider = litellm_params.get("custom_llm_provider")
+                    return base_model, custom_llm_provider
+
                 resolved_model = litellm_params.get("model")
 
                 if resolved_model:
                     verbose_proxy_logger.debug(
                         f"Resolved model '{model}' to '{resolved_model}' from router"
                     )
-                    # Extract custom_llm_provider if present
                     custom_llm_provider = litellm_params.get("custom_llm_provider")
                     return resolved_model, custom_llm_provider
         except Exception as e:

tests/test_litellm/proxy/management_endpoints/test_cost_tracking_settings.py

@@ -270,3 +270,123 @@ class TestCostTrackingSettings:
             assert "error" in response_data["detail"]
             assert "STORE_MODEL_IN_DB" in response_data["detail"]["error"]
 
+
+
+class TestResolveModelForCostLookup:
+    """Tests for _resolve_model_for_cost_lookup base_model resolution."""
+
+    def test_resolves_base_model_for_azure_deployment(self):
+        """
+        When a model group has base_model set in model_info,
+        _resolve_model_for_cost_lookup should return the base_model
+        instead of the raw litellm_params.model (Azure deployment name).
+        """
+        from litellm.proxy.management_endpoints.cost_tracking_settings import (
+            _resolve_model_for_cost_lookup,
+        )
+
+        mock_router = MagicMock()
+        mock_router.get_model_list.return_value = [
+            {
+                "model_name": "gpt-5.3-codex",
+                "litellm_params": {
+                    "model": "azure/openai/gpt-5.3-codex",
+                    "api_base": "https://fake.openai.azure.com/",
+                    "api_key": "fake-key",
+                },
+                "model_info": {
+                    "id": "test-id",
+                    "base_model": "azure/gpt-4o",
+                },
+            }
+        ]
+
+        with patch(
+            "litellm.proxy.proxy_server.llm_router",
+            mock_router,
+        ):
+            resolved_model, provider = _resolve_model_for_cost_lookup("gpt-5.3-codex")
+
+        assert resolved_model == "azure/gpt-4o"
+        mock_router.get_model_list.assert_called_once_with(model_name="gpt-5.3-codex")
+
+    def test_falls_back_to_litellm_params_model_when_no_base_model(self):
+        """
+        When no base_model is set, should fall back to litellm_params.model.
+        """
+        from litellm.proxy.management_endpoints.cost_tracking_settings import (
+            _resolve_model_for_cost_lookup,
+        )
+
+        mock_router = MagicMock()
+        mock_router.get_model_list.return_value = [
+            {
+                "model_name": "gpt-4",
+                "litellm_params": {
+                    "model": "openai/gpt-4",
+                },
+                "model_info": {
+                    "id": "test-id",
+                },
+            }
+        ]
+
+        with patch(
+            "litellm.proxy.proxy_server.llm_router",
+            mock_router,
+        ):
+            resolved_model, provider = _resolve_model_for_cost_lookup("gpt-4")
+
+        assert resolved_model == "openai/gpt-4"
+
+    def test_resolves_base_model_from_litellm_params(self):
+        """
+        When base_model is in litellm_params (not model_info),
+        it should still be resolved.
+        """
+        from litellm.proxy.management_endpoints.cost_tracking_settings import (
+            _resolve_model_for_cost_lookup,
+        )
+
+        mock_router = MagicMock()
+        mock_router.get_model_list.return_value = [
+            {
+                "model_name": "my-azure-model",
+                "litellm_params": {
+                    "model": "azure/my-custom-deployment",
+                    "base_model": "azure/gpt-4o-mini",
+                },
+                "model_info": {
+                    "id": "test-id",
+                },
+            }
+        ]
+
+        with patch(
+            "litellm.proxy.proxy_server.llm_router",
+            mock_router,
+        ):
+            resolved_model, provider = _resolve_model_for_cost_lookup(
+                "my-azure-model"
+            )
+
+        assert resolved_model == "azure/gpt-4o-mini"
+
+    def test_returns_original_model_when_no_router(self):
+        """
+        When no router is available, should return the original model name.
+        """
+        from litellm.proxy.management_endpoints.cost_tracking_settings import (
+            _resolve_model_for_cost_lookup,
+        )
+
+        with patch(
+            "litellm.proxy.proxy_server.llm_router",
+            None,
+        ):
+            resolved_model, provider = _resolve_model_for_cost_lookup(
+                "azure/openai/gpt-5.3-codex"
+            )
+
+        assert resolved_model == "azure/openai/gpt-5.3-codex"
+        assert provider is None