typed/recipes

Models

Every model released as a System One model, with its price, limits, and where the numbers come from. More will be added as they ship.

Jev

TypeSafe AI
Status
Early access, hosted API
License
Closed weights
Price
$0.042 per million input tokens, output free
Latency
70–500 ms end to end (vendor figure)

The first model sold as a System One model. You send text and typed questions to a hosted endpoint and get back typed answers with probabilities. It writes no prose.

Jev details

Laya

Convai Innovations
Status
Open weights, self-hosted
License
Apache 2.0
Price
$0 per token; you pay for your own hardware
Latency
32.8 ms single question on a T4 GPU; 7.2 ms per question in batches of 10 (vendor figures)

An open-weight model that answers the same three question types as Jev and runs on your own GPU or CPU. Three checkpoints ship: English (421M), multilingual for 100+ languages (322M), and one tuned on typed decisions (421M).

Laya details

Know of another System One model? Submit it.

Continue learning