AI Agent StoreTypeSafe AI · Hosted decision route
Jev
Choose a label, score or yes/no probability for a support ticket, document or other text. Jev is a decision service rather than a chatbot.
Announced 2026-09-16 · First reviewed 2026-10-04 · Checked 2026-11-03. The announcement and discovery dates do not establish ordinary API availability. Unverified prices remain unknown.
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. The exact evaluation contract accepts text state and typed Choice, Score and Boolean questions. It does not stream free-form output; no independent speed advantage or calibrated confidence is inferred.
Native jev-latest and jev-preview both select 1.14.0 at this check. Use an exact version for repeatable tests. These native aliases do not establish which version the unversioned Gateway offer serves. Gateway uses the fixed-choice evaluation endpoint rather than free-form chat.
Gateway declares 32,000 tokens for shared state plus the longest question, and 64,000 total request tokens. This is not a 64K single-state context. The maximum question count is unverified.
Output: Typed choices, rubric scores and Boolean probabilities. Compare decision models, limits and input costs ↗
Gateway quotes $0.042 per million billed input tokens and no output-token charge. Its model page rounds the input quote to $0.04; this calculator uses the exact catalog rate. 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 ↗