fix(router): treat malformed configured token limits as absent on /v1/models (#33864)

A deployment whose model_info carried a non-numeric max_input_tokens or
max_output_tokens (for example "128,000" or an empty string) made the
bare int() in get_configured_token_limits raise inside the per-model
/v1/models loop, so one misconfigured deployment turned the entire
listing into a 500. Coerce each configured limit safely and treat
malformed values as absent, matching the graceful degradation the
listing had before the cost-map switch

litellm/router.py

@@ -8535,7 +8535,8 @@ class Router:
         Return (max_input_tokens, max_output_tokens) explicitly configured in a concrete
         deployment's model_info for model_name, via O(1) index lookup.
 
-        Returns (None, None) for wildcard-expanded or unknown names. Unlike
+        Returns (None, None) for wildcard-expanded or unknown names, and treats a
+        malformed configured value as absent rather than failing the listing. Unlike
         get_model_group_info, this never triggers pattern matching or deep copies, so it
         is safe to call per listed model on the /v1/models hot path.
         """
@@ -8543,12 +8544,18 @@ class Router:
         if deployment is None:
             return (None, None)
 
+        def _as_int(value: object) -> "int | None":
+            if value is None or isinstance(value, bool):
+                return None
+            try:
+                return int(value)
+            except (TypeError, ValueError):
+                return None
+
         model_info = deployment.model_info
-        max_input = model_info.get("max_input_tokens")
-        max_output = model_info.get("max_output_tokens")
         return (
-            int(max_input) if max_input is not None else None,
-            int(max_output) if max_output is not None else None,
+            _as_int(model_info.get("max_input_tokens")),
+            _as_int(model_info.get("max_output_tokens")),
         )
 
     def get_deployment_credentials_with_provider(

tests/test_litellm/proxy/test_proxy_utils.py

@@ -556,6 +556,31 @@ def test_create_model_info_response_deployment_limits_override_cost_map():
     assert response["max_output_tokens"] == 16384
 
 
+def test_create_model_info_response_survives_malformed_configured_limits():
+    from litellm import Router
+
+    router = Router(
+        model_list=[
+            {
+                "model_name": "bad-limit-model",
+                "litellm_params": {"model": "openai/some-unmapped-model"},
+                "model_info": {"max_input_tokens": "128,000"},
+            }
+        ]
+    )
+
+    response = create_model_info_response(
+        model_id="bad-limit-model",
+        provider="openai",
+        llm_router=router,
+        get_model_info=_raise_unmapped,
+    )
+
+    assert response["id"] == "bad-limit-model"
+    assert "max_input_tokens" not in response
+    assert "max_output_tokens" not in response
+
+
 def test_create_model_info_response_emits_integer_token_counts():
     response = create_model_info_response(
         model_id="some-model",

tests/test_litellm/test_router.py

@@ -5775,3 +5775,34 @@ def test_get_configured_token_limits_skips_wildcard_pattern_matching():
         assert router.get_configured_token_limits(
             "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"
         ) == (None, None)
+
+
+def test_get_configured_token_limits_treats_malformed_values_as_absent():
+    malformed = ["", "unlimited", "128,000", [128000], {"max": 128000}, True]
+    router = litellm.Router(
+        model_list=[
+            {
+                "model_name": f"bad-limit-{i}",
+                "litellm_params": {"model": "openai/some-unmapped-model"},
+                "model_info": {"max_input_tokens": bad, "max_output_tokens": bad},
+            }
+            for i, bad in enumerate(malformed)
+        ]
+    )
+
+    for i in range(len(malformed)):
+        assert router.get_configured_token_limits(f"bad-limit-{i}") == (None, None)
+
+
+def test_get_configured_token_limits_coerces_numeric_strings():
+    router = litellm.Router(
+        model_list=[
+            {
+                "model_name": "quoted-limits-model",
+                "litellm_params": {"model": "openai/some-unmapped-model"},
+                "model_info": {"max_input_tokens": "32000", "max_output_tokens": "8000"},
+            }
+        ]
+    )
+
+    assert router.get_configured_token_limits("quoted-limits-model") == (32000, 8000)