The 2m context window is great from the latest Gemini models, but 8k output tokens is far less than competitors models. Of course for text data, you can ask the model to continue, however for json validated outputs, it’s not as straightforward.

Hi, Welcome to the forum. Do you have a good use or example? Eventually, it might be better to open an issue here: https://issuetracker.google.com Cheers.

I’m running into the same issue, I want to use Google Gemini 2.0 Flash to take call recordings from my call center and transcribe them and provide classification and or feedback/context and return a structured json with the desired format, currently for a 50 minute conversation the 8K context is exa…

Any nice way to output more than 8k tokens of structured json?

Gemini API

Krish_Varnakavi1 June 13, 2025, 9:15pm 6

Hi @bondioso,

Are you still facing the issue?

Topic		Replies	Views
Clarification on Gemini Output Limit (8192 tokens) for API Access and Latest Models — Need 20k+ Tokens Gemini API api	1	1589	March 18, 2025
How to expand Gemini output window Gemini API help-request , new-features	6	1790	October 9, 2024
Can I increase max_output_tokens Gemini API api , models	2	3339	December 18, 2024
Tips on how to increase token output size in GenerateContentResponse? Gemini API gemini-15 , api , models	1	678	September 28, 2024
Handling Token Limits in Gemini-1.5-Flash API Responses Gemini API gemini-15 , api	1	213	September 27, 2024

Any nice way to output more than 8k tokens of structured json?

Related topics