This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Accept
Reject
Preferences
Log in to ask a question
Get hands-on experience with 20+ free Google Cloud products and $300 in free credit for new customers.
Log in to ask a question

Turn off thinking for gemini-2.5-flash batch api in Vertex AI

Posted a week ago
xyzpoka
Bronze 1
Bronze 1
Reply posted on --/--/---- --:-- AM

gemini-2.5-flash-preview-05-20 support batch predications now (2025-05-21), doc is here: 

Gemini 2.5 Flash  |  Generative AI on Vertex AI  |  Google Cloud

I want to use gemini-2.5-flash batch api (Python) in Vertex AI, I want to turn off thinking (thinkbudget=0), How to turn it off in config?

Solved Solved
0 3 638
Topic Labels
Jump to Solution
0 Likes
1 ACCEPTED SOLUTION

Posted on --/--/---- --:-- AM
ericdong
Staff
Reply posted on --/--/---- --:-- AM

GenerationConfig should be in input JSONL or the BigQuery table. See examples here: https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/batch-prediction/intro_batch_p...

Note that Gemini 2.5 Flash does not yet support batch prediction.

View solution in original post

Jump to Solution
0 Likes
3 REPLIES 3