From 6c6b26f35dd27497d8d3e4118d173fba95d5c048 Mon Sep 17 00:00:00 2001
From: Praveen11558 <44603409+Praveen11558@users.noreply.github.com>
Date: Tue, 24 Mar 2026 23:39:42 +0530
Subject: [PATCH] Update litellm/litellm_core_utils/llm_cost_calc/utils.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---
 litellm/litellm_core_utils/llm_cost_calc/utils.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py
index 771b272d94e..acd3bbfc78d 100644
--- a/litellm/litellm_core_utils/llm_cost_calc/utils.py
+++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py
@@ -677,7 +677,9 @@ def generic_cost_per_token(  # noqa: PLR0915
     # without being included in the per-token detail fields. When any of these are
     # active, a gap between accounted_tokens and prompt_tokens is expected and must
     # NOT be filled:
-    #   - character_count / video_length_seconds: replace per-token billing entirely
+    #   - character_count / video_length_seconds: the token gap between accounted_tokens
+    #     and prompt_tokens is already covered by character/video-second billing; filling
+    #     the gap into text_tokens would double-bill that content at the text rate.
     #   - image_count: additive flat-rate billing; the image-URL tokens are already
     #     reflected in prompt_tokens and billed separately via input_cost_per_image
     has_non_token_alternative_billing = (