scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 114

token_count calculation during inline data sent during multimodal inputs

Browse source
This commit is contained in:
Praveen11558 2026-03-05 12:28:06 +05:30 • committed by GitHub
parent 86d9535ab8
commit dd3bcd3421
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/litellm_core_utils/llm_cost_calc/utils.py
View file

@ -663,7 +663,7 @@ def generic_cost_per_token( # noqa: PLR0915
accounted_tokens = text_tokens + cache_hit + audio_tokens + cache_creation + image_tokens
has_double_counting = cache_hit > 0 and accounted_tokens > usage.prompt_tokens
# Double-counting fix (xAI etc.): recalculate text_tokens from scratch
if has_double_counting:
if (text_tokens == 0 and prompt_tokens_details["image_count"] == 0) or has_double_counting:
text_tokens = (
usage.prompt_tokens
- cache_hit