It's all trade-offs between price, speed and accuracy. It's no good using a free model when the latency is 10s+ and the throughput is sub 100token/s and this is often the case on OpenRouter. I have to use a speedy provider like Groq and a small model.
Dumber models need a lot more context to correct the inaccuracies. I'm mostly using mid tier models like Gemini 3 flash to generate the boards and then I use the fastest models to answer questions (currently gpt-oss-120b on Groq).
I disagree. UX could be improved but for an alpha version I found out it was easy to use. The main feature "Guess" should be probably more prevalent though. Also for me it did not seem sluggish but that might depend on a lot of factors.
but for yes no game you can probably use a cheaper and smaller model and free credits ritght? Anyway, this sounds good geeky.
It's all trade-offs between price, speed and accuracy. It's no good using a free model when the latency is 10s+ and the throughput is sub 100token/s and this is often the case on OpenRouter. I have to use a speedy provider like Groq and a small model. Dumber models need a lot more context to correct the inaccuracies. I'm mostly using mid tier models like Gemini 3 flash to generate the boards and then I use the fastest models to answer questions (currently gpt-oss-120b on Groq).
Pretty cool!!
this is pretty cool !
Sluggish as hell. Horrible UX. Overcomplicated.
I disagree. UX could be improved but for an alpha version I found out it was easy to use. The main feature "Guess" should be probably more prevalent though. Also for me it did not seem sluggish but that might depend on a lot of factors.