TypeSafe AI · Decision model · Last verified 2026-10-15
Jev (TypeSafe AI)
Partly verified
Hosted "System One" decision model from TypeSafe AI: send a state plus typed questions (noul, choice, score) to POST /v1/systemone and get probabilities back. Current versions jev-1.14.0 and jev-1.13.0.
What it does
- Endpoint: https://api.typesafe.ai/v1/systemone; model IDs jev-1.14.0 and jev-1.13.0 (aliases such as jev-latest also used in docs).
- Question types: noul (yes/no probability), choice, score. The System One request shape is also used by several other vendors.
- No separate limit on number of questions; requests must fit the context limits.
Pricing
- $0.042 per 1M input tokens ($42 per billion) for both Jev 1.14 and 1.13; output tokens free. Long-context mode costs the same per token. [Verified 2026-10-15 on docs.typesafe.ai/models]
Limits
- 64k tokens per request / 32k per question by default; 262k for both with the opt-in long-context header (slower and less accurate per TypeSafe). [Verified 2026-10-15 on docs.typesafe.ai/models]
Status
- Jev 1.14 available from October 14, 2026 per TypeSafe docs. [Verified 2026-10-15 on docs.typesafe.ai/models]
- Correction: an earlier version of this page showed $0.42/1M taken from jevtypesafeai.com, a domain we could not tie to TypeSafe. TypeSafe’s own docs show $0.042. [Correction logged 2026-10-15]
Safety & fit notes
- Pin a versioned ID (e.g. jev-1.13.0) rather than an alias so thresholds don’t drift with version changes.
- Text-oriented; check image support for your version in TypeSafe docs before relying on it.