JevMade hello@JevMade.com
← Back to evaluation videos

JevMade field notes / Video guide

Is Jev Really Better, Faster and Cheaper? I Put Jev To Test vs. Luna

Edward Donner puts TypeSafe AI's Jev model to the test against GPT-4.1-Nano and GPT-5.6 Luna on estimating retail prices for 200 products. He explains Jev's non-autoregressive single-pass decision architecture, evaluates speed and accuracy trade-offs, and clarifies what TypeSafe AI's 'cannot hallucinate' claim actually means in classification workflows.

Original by Edward DonnerEvaluationIntermediate10 min 26 sec Published Source reviewed

Before you press play

What you’ll find in the video

  1. Jev generates decisions in a single pass to match an output specification rather than streaming token-by-token like autoregressive models.
  2. In Donner's 200-item pricing test, single-pass Jev was roughly 4x faster than Luna but cost around 8 cents per thousand requests versus Luna's 3 cents.
  3. A 'no hallucination' claim means Jev is constrained to valid specification choices, not that its predicted decisions or classifications are always correct.
Worth knowing

Auto-generated English captions reviewed with Gemini. Results are from a specific 200-product price prediction experiment accessed via an OpenRouter alpha endpoint, where Jev proved more expensive per thousand requests than non-reasoning Luna.

Is Jev Really Better, Faster and Cheaper? I Put Jev To Test vs. Luna