On: Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

[buildwithdennis]

I assume the cost is whatever you run the model on. Jev is already dirty cheap, $0.42 per million input tokens and output is free and the input cost is covering tokenization + API utilization

[bilekas → buildwithdennis]

Well, I'm no expert, but this runs on Qwen3.5 and Gemma 4, stripped down, but they're pretty pricey.

[rahimnathwani → buildwithdennis]

$0.042 not $0.42