phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Gemini 2.5 Flash output cost is based on thinking enabled

Browse source
This commit is contained in:
Andrew Wesie 2025-04-20 17:17:05 -05:00
parent 0b63c7a2eb
commit 58c2551fa6
7 changed files with 74 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

3
litellm/utils.py
View file

@ -4557,6 +4557,9 @@ def _get_model_info_helper( # noqa: PLR0915
"output_cost_per_token_batches"
),
output_cost_per_token=_output_cost_per_token,
output_cost_per_token_thinking=_model_info.get(
"output_cost_per_token_thinking", None
),
output_cost_per_audio_token=_model_info.get(
"output_cost_per_audio_token", None
),