-
-
Notifications
You must be signed in to change notification settings - Fork 222
-
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!
Beta Was this translation helpful? Give feedback.
All reactions
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
-
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.
Beta Was this translation helpful? Give feedback.
All reactions
-
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!
Beta Was this translation helpful? Give feedback.