Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Gemini model response truncated #465

Answered by Vali-98
kaibagley asked this question in Q&A
Discussion options

Hey, thanks for the great app.everything works fine with a non reasoning model like Claude 3.7 Sonnet, but when using Gemini 2.5 Pro (all via OpenRouter) its response is cut off to around 20 characters.

Increasing the generated tokens does allow the response to be longer, but I have to have generated tokens set quite high for a full response, who h reduces the context significantly...

I've seen a few issues like this on GH, but simply increasing the generated tokens slider doesn't seem like it actually solves the issue, so I'm not sure what to do here

Thanks!

You must be logged in to vote

Increasing the generated tokens does allow the response to be longer, but I have to have generated tokens set quite high for a full response, who h reduces the context significantly...

Iirc OR model context lengths can be set in the app. Is there any reason why you can't set your Max Context to say, 32k and response length to 1k? Testing this on my device via OR w/ Gemini 2.5 Pro it seems to work fine.

Replies: 1 comment 1 reply

Comment options

Increasing the generated tokens does allow the response to be longer, but I have to have generated tokens set quite high for a full response, who h reduces the context significantly...

Iirc OR model context lengths can be set in the app. Is there any reason why you can't set your Max Context to say, 32k and response length to 1k? Testing this on my device via OR w/ Gemini 2.5 Pro it seems to work fine.

You must be logged in to vote
1 reply
Comment options

Ahhhhhhh yes, there's no reason I can't do that. For some reason I thought I had to balance 8k tokens between context and generated tokens. which is clearly not the case.

Thanks for the reply!

Answer selected by kaibagley
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /