AI Agent StoreTypeSafe AI · Provider documented
Jev 1.14.0 · Gateway
Choose a fixed Jev version when you need repeatable ticket routing, labels or scores. Retest your confidence threshold before changing versions.
Released 2026-10-14 · First reviewed 2026-10-16 · Checked 2026-11-03.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact AI Gateway route ID: typesafe-ai/jev-1.14.0. The native model table describes text input; Gateway also tags vision. Image support for this exact route remains unresolved, so this page does not promise it.
Native jev-latest and jev-preview now both select 1.14.0; there is no separate preview build at this check. Request an exact version for reproducible tests. Gateway uses the separate ID shown here.
Gateway lists 32,000 tokens. Native Jev documents 32,000 for shared information plus one question and 64,000 for the whole request. Its optional longer-context header is not assumed to work through Gateway.
Output: Choices, ordered scores and yes/no probabilities. Compare decision models, limits and input costs ↗
The same input quote does not prove equal accuracy. Compare both versions on your own labeled examples. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Check whether confidence scores match the answers you can verify.
Compare caching and long-context costs ↗