TypeSafe's Jev is a lightweight decision model that classifies and routes decisions without generating text. It matches GPT-4's 68% accuracy at $0.0004 per case and 0.4 seconds, versus Opus's $0.18 and 38 seconds, making it 440 times cheaper while trading five accuracy points for speed and cost.
TypeSafe's Jev. So Jev is the latest hotness, 440 times cheaper, 109 times faster than the competition with their System 1 models, which introduces a new class of models. One of the use cases is LM judges. So can TypeSafe's Jev decision models replace LM judges? TypeSafe's Jev classifies scores and routes without generating text, up to hundreds of times cheaper than an LM judge. What that changes for evals, conference routing, application architecture. So JEV versus LLMs, early benchmarks on accuracy, cost, and latency averaged across the 4 workflows. JEV lands at 68% accuracy at $0.0004 and 0.4 seconds per case. GPT-5.6 Terra is at 68% for 3 cents. So that is a couple of orders of magnitude difference and then 10 seconds. So a couple orders of magnitude difference on both costs. And speed. Opus 5 is at 73% for 18 cents and 38 seconds. So that's 5 points behind Opus 5, which is the leader. But on the other hand, it's 440x cheaper. That's a very interesting cost-benefit trade-off, such a radical one that may change how we architect applications.
