[gaiagraphia]

It'd be nice if you could see how much each request actually cost in relation to your plan, and to have some type of easily accessible meter.

A lot of AI providers operate in black box territory when it comes to limits, which is quite annoying.

[moebrowne]

> We plan to display cost and interaction details more prominently soon, potentially on the billing page or directly within the Assistant interface.

I too want to see this soon. As a long time user of Ultimate it isn't uncommon for me to use 5M tokens per month and I have no idea if this will be covered by my subscription now.

[cyberpunk]

How do you know how many tokens you've used? Or is it a guesstimate?

[gaiagraphia]

The following should say your daily token usage:

https://kagi.com/settings?p=consumption

[KoolKat23]

And what is the cheapest model to use? Llama 70B?

[VHRanger]

https://help.kagi.com/kagi/ai/llm-benchmark.html

gemini flash, 4o-mini, mistral small for super cheap

qwen-qwq for strong models

[KoolKat23]

Thanks