Jev guides
Jev AI guides for the decision layer.
Independent explainers, API notes, and evaluation checklists for TypeSafe’s Jev System One model.
01
Start here
↗02What is Jev AI? TypeSafe’s System One model explained
Typed decisions versus text generation, current model jev-1.13.0, and where Jev fits.
Quickstart
↗03How to use Jev: API, SDKs, and first request
Endpoint, keys, Python and curl examples, and how to pin a version.
Access
↗04How to get Jev access
TypeSafe console keys versus Vercel AI Gateway’s typesafe-ai/jev.
Licensing
↗05Is Jev open source? What developers should verify
Hosted model, no public weights, and how to talk about community clones.
Compare
↗06Jev vs GPT: a practical architecture decision
Use a decision layer around a general model instead of one model for every branch.
Compare
↗07Jev vs Claude: gate the expensive reasoning pass
Let Jev approve or route, then spend Claude tokens only when the work needs language.
Cost
↗08Jev pricing: $0.042 per million input tokens
Input-only billing, free output, and a simple token calculator.
Evaluation
↗How to benchmark a Jev decision layer
Accuracy, calibration, latency, fallback, and downstream outcomes.