How I AI · Monday, September 28, 2026
A new AI model called Jev from TypeSafe AI is designed for making decisions and classifying data, differentiating itself from standard LLMs by outputting predefined 'TypeSafe values' rather than just text strings. The model is noted for its speed and low cost, with input tokens priced at 4 cents per million and no charge for output tokens.
“With the standard LLMs that you're used to working with, you are getting strings and generated text outputs. So you're getting text in, text out. With Jev, you're getting text in, TypeSafe values out.”
“And so if you look at the current cost of input and output tokens, it can be pennies to hundreds of dollars per million output tokens. Jev only charges you on input tokens because it barely outputs anything. And it is 4 cents per million input tokens.”
“Basically, it tells you what the likelihood that the answer to a question is yes. So if the answer to a question is yes or no, it's Clara podcaster, it's going to give you like a 99% null.”