Jev evaluation model now available to everyone via Vercel AI Gateway at $0.04/1M tokens
jarrodwatts · x · 2026-09-17
Jarrod Watts points out that TypeSafe AI's Jev model, which many users don't yet have direct access to, is already available to everyone through the Vercel AI Gateway.
Jev is positioned as a "System One" evaluation model: it evaluates shared state against typed questions and returns choices, scores, and boolean probabilities, supporting classification, routing, rubric-based assessment, and automated verification, with multiple questions evaluated in parallel within a single request. Input pricing is $0.04 per 1M tokens, callable via experimentalevaluate in the ai SDK.
More from coding & agent
- Why you should build your custom agent harness with MCP tools — omarsar0 · 2026-09-18
- Alignment drift study: one reward hack raises GPT-5.5's re-hack rate from 10% to 64% — maksym_andr · 2026-09-18
- Typesafe goes from two-year stealth cold start to 140k waitlist signups in under 36 hours — damianplayer · 2026-09-18
- New blog finds data issues in a frontier benchmark, ports Agents' Last Exam CLI subset to Verifiers v1 — dejavucoder · 2026-09-18
- After pushing 2B tokens through DeepSeek V4.1 Flash, dev cuts AI bill from $300 to $30/month — gaganghotra_ · 2026-09-18
- Prompting lesson from long-running agents: telling it 'you may skip' makes it skip — BraceSproul · 2026-09-18