Decider 1: probabilities for every option in a decision

Decider 1 is ours, built at meraGPT. It is a hosted decision model. You send a piece of state plus yes/no, choice, or score questions, and get back a probability for every option. Pricing is $0.03 per million input tokens, and new accounts get free trial credit.

The playground needs no signup: https://meragpt.com/playground

On the open typed-decisions benchmark on Hugging Face (zero-shot table), it scores 0.768 accuracy, ahead of Liquid d1 at 0.742 and Jev at 0.727. We maintain that benchmark. As a small demo on a synthetic folder, it sorted 184 desktop files into 8 folders from file names alone, 96.2% correct.

What decisions in your product would you route to something like this?