読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニュースクイックテイク1 分で読めるDisconfirmAI 編集部

Decision model Jev launches charging input only, output free

Jev turns the LLM into a text-in, number-out classifier at a new price shape, but performance claims remain vendor-only; build your own evals before adopting.

2026-09-22 07:09 GMT+8

TypeSafe AI has launched Jev: text in, floating-point numbers out, billed on input only at $0.042 per million tokens, with output free.

It answers three kinds of questions—yes/no, choice, and score—fitting classification tasks like spam filtering, labeling, and reranking. The vendor's own jaggedness documentation concedes it is currently weak on numbers, dates, and adversarial content.

Speed and cost claims are vendor-stated with no independent evaluation. Simon Willison notes the model returns only a number with no explanation of its judgment, making bias a sharper risk in uses like ranking job applicants.

ソース

  • simonwillison.net↗
リサーチを続ける →
ログイン / 新規登録
読書リサーチレーダー投資フレームワーク