TypeSafe Jev now available in AI Gateway
By Steven Van ·
Jev answers typed yes/no, choice, and score questions with calibrated probabilities in 70-500ms, instead of generating prose.
TypeSafe's Jev model is now available through Netlify's AI Gateway with no configuration needed. Installing the @typesafe-ai/sdk package and calling it from a Netlify Function requires no API keys, no provider setup, and no base URL. AI Gateway handles credentials automatically, and usage is billed to Netlify credits like every other model in the gateway.
Jev is TypeSafe's first "System One" model, and it works differently from chat models. Instead of generating prose, it takes program state plus a set of typed questions and returns typed answers with calibrated probabilities. There are three question types: choice picks one option from a set, score rates against ordered levels, and noul returns a yes/no probability between 0 and 1. Answers are constrained to the options declared in the request, so there is no JSON parsing or schema coercion needed on the response.
Every question in a request is evaluated in parallel against the same state, so batching a dozen questions into one call costs little more than asking one. State and questions share a budget of roughly 32,000 tokens, about 150,000 characters of English text, and TypeSafe reports end-to-end response times of 70 to 500 milliseconds, which the company points to for classification, routing, extraction, scoring, and guardrail checks on the request path.
The SDK defaults to the jev-latest alias, currently jev-1.13.0, and requires Node.js 20 or newer.