From 1248c9356741577e8829320579ac66f5817f8cba Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Wed, 23 Sep 2026 02:58:55 +0000
Subject: [PATCH] fix(vertex_ai): preserve tiered rate type narrowing

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 litellm/llms/vertex_ai/cost_calculator.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/litellm/llms/vertex_ai/cost_calculator.py b/litellm/llms/vertex_ai/cost_calculator.py
index e0a79e00ab3..575442cda02 100644
--- a/litellm/llms/vertex_ai/cost_calculator.py
+++ b/litellm/llms/vertex_ai/cost_calculator.py
@@ -194,7 +194,7 @@ def _handle_128k_pricing(
     base_input_rate: Final = model_info["input_cost_per_token"] or 0.0
     above_tier: Final = input_cost_per_token_above_128k_tokens is not None and _is_above_128k(tokens=tier_tokens)
 
-    input_rate: Final = input_cost_per_token_above_128k_tokens if above_tier else base_input_rate
+    input_rate: Final = (input_cost_per_token_above_128k_tokens or base_input_rate) if above_tier else base_input_rate
 
     cache_read_rate: Final = model_info.get("cache_read_input_token_cost") or input_rate
     cache_creation_rate: Final = model_info.get("cache_creation_input_token_cost") or base_input_rate