A request sends one state, the text to evaluate, plus a set of named questions, and comes back with a typed answer under each name. All the questions in a call run against the same state, so asking four things about one ticket costs one round trip to POST https://api.typesafe.ai/v1/systemone.
The shipping version is jev-1.13.0. The aliases jev-latest and jev-preview both point at it. Input costs $0.042 per million tokens and output is free. A request carries 64k tokens in total, with 32k as the ceiling on the state plus the longest single question. Rate limits are 250,000 tokens per second and 1,200 requests per minute. Input is text only, as a string, a JSON object, or an array of text values, so images and audio have to be converted before they go in.
TypeSafe claims end-to-end times of 70ms to 500ms and a 40x to 200x speedup over frontier models at the same level of intelligence on System One tasks. Both numbers are the vendor’s own, and no independent benchmark had been published as of 2026-09-18.
TypeSafe also publishes a jaggedness page for jev-1.13 listing nine weak spots, among them arithmetic and date comparison. Full specs are on the Jev model page, and the cost math is in Jev speed and pricing.