TypeSafe AI
San Francisco lab behind Jev, a model that returns typed decisions instead of text.
TypeSafe AI is a San Francisco AI lab building what it calls System One models, made to be called by software rather than chatted with. Jev, its first, reads a state given as text and answers yes/no, multiple-choice and scale questions about it with typed values and calibrated probabilities. It generates no text, code or explanations.
typesafe.aiCall TypeSafe AI models through Opper with one API key. Sign up without a credit card.
Models from TypeSafe AI
| Model | Context | Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|---|---|
| 64K | Multi | No | $0.04 | — | Input price | |||
| 64K | Multi | No | $0.04 | — | Input price |
Release timeline
Every dated TypeSafe AI release, newest first — 2 of 2 run on the Opper gateway today. Releases without a published date aren't listed. See the TypeSafe AI release timeline.
2 releases in the last 12 months29 days median gap29–29 days range