Jev
- In Input modalities: Text
- Confidence scores
Decision models return typed values (such as a choice or a score) instead of text. Compare them with other decision models, not with language models.
Prices
1 offering · prices as listed| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.042 | Free |
Prices from Models - TypeSafe (opens in a new tab) (checked Nov 8, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Open weights
- —
- Model ID
Not stated on TypeSafe’s pages: single pass.
Cited scores
From third-party leaderboards, not measured by usNo independent benchmark covers decision models yet. We will cite one when it exists rather than invent a score.
News
All news →- Sep 15, 2026Release TypeSafe releases Jev (preview) 64K-token context window. On TypeSafe API: $0.042 input, $0.00 output per 1M tokens.
Changes
All changes →- New decision model
Sources
- Introducing System One models & Jev (opens in a new tab) typesafe.ai · checked Nov 6, 2026
- Models - TypeSafe (opens in a new tab) docs.typesafe.ai · checked Nov 8, 2026
- TypeSafe docs: introduction (opens in a new tab) docs.typesafe.ai · checked Sep 26, 2026
- State - TypeSafe AI (opens in a new tab) docs.typesafe.ai · checked Nov 3, 2026
- Introducing System One Models & Jev - TypeSafe AI Blog (opens in a new tab) typesafe.ai · checked Nov 7, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
TypeSafe · United States · typesafe.ai
Related models
Snapshots, the same family and other models from this provider