From 6b755cfce20a64065b4a23d2401574feba839190 Mon Sep 17 00:00:00 2001
From: Abdullah Habib Biswas <ahb7@users.noreply.github.com>
Date: Sun, 1 Feb 2026 04:46:07 +0530
Subject: [PATCH] fix: prevent error when max_fallbacks exceeds available
 models (#20071)

---
 .../router_utils/fallback_event_handlers.py   | 12 +++++-
 tests/test_fallbacks.py                       | 42 +++++++++++++++++++
 2 files changed, 52 insertions(+), 2 deletions(-)

diff --git a/litellm/router_utils/fallback_event_handlers.py b/litellm/router_utils/fallback_event_handlers.py
index 62e706a0cf5..738b82d7023 100644
--- a/litellm/router_utils/fallback_event_handlers.py
+++ b/litellm/router_utils/fallback_event_handlers.py
@@ -113,8 +113,16 @@ async def run_async_fallback(
         The most recent exception if all fallback model groups fail.
     """
 
-    ### BASE CASE ### MAX FALLBACK DEPTH REACHED
-    if fallback_depth >= max_fallbacks:
+    ### BASE CASE ### MAX FALLBACK DEPTH REACHED 
+    if fallback_depth >= max_fallbacks: 
+        raise original_exception
+
+    ### CHECK IF MODEL GROUP LIST EXHAUSTED
+    if original_model_group in fallback_model_group:
+        fallback_group_length = len(fallback_model_group) - 1
+    else:
+        fallback_group_length = len(fallback_model_group) 
+    if fallback_depth >= fallback_group_length:
         raise original_exception
 
     error_from_fallbacks = original_exception
diff --git a/tests/test_fallbacks.py b/tests/test_fallbacks.py
index bc9aa4c64c8..c22cefa6be6 100644
--- a/tests/test_fallbacks.py
+++ b/tests/test_fallbacks.py
@@ -336,3 +336,45 @@ async def test_chat_completion_bad_and_good_model():
             f"Iteration {iteration + 1}: {'✓' if success else '✗'} ({time.time() - start_time:.2f}s)"
         )
         assert success, "Not all good model requests succeeded"
+
+
+@pytest.mark.asyncio
+async def test_router_fallback_exhaustion():
+    """
+    Test for Bug 19985:
+    """
+    from litellm import Router
+    import pytest
+
+    # Setup: Only ONE fallback model available
+    model_list = [
+        {
+            "model_name": "gpt-3.5-turbo",
+            "litellm_params": {"model": "openai/fake", "api_key": "bad-key"},
+        },
+        {
+            "model_name": "bad-model-1",
+            "litellm_params": {"model": "azure/fake", "api_key": "bad-key"},
+        }
+    ]
+
+    # max_fallbacks=10 is much larger than the 1 fallback provided in the list
+    router = Router(
+        model_list=model_list,
+        fallbacks=[{"gpt-3.5-turbo": ["bad-model-1"]}],
+        max_fallbacks=10
+    )
+
+    try:
+        # This will fail and attempt to fallback
+        await router.acompletion(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": "test"}]
+        )
+    except Exception as e:
+        # The success criteria is that we DON'T get an IndexError
+        assert not isinstance(e, IndexError), f"Expected API error, but got IndexError: {e}"
+        # Also ensure we actually hit a fallback attempt
+        print(f"Caught expected exception: {type(e).__name__}")
+
+