Jev 1.13: the current public model
As of the public models page, the current versioned model is jev-1.13.0. The aliases jev-latest and jev-preview both point at that ID. There is no separate preview build until TypeSafe ships one.
The jaggedness note applies to jev-1.13 and was last reviewed 2026-09-17.
Published envelope
From the models page (confirm there before you bid a contract):
- Price: $42 / billion input tokens, $0.042 / million. Output tokens are free.
- Rate limits: 250,000 tokens per second and 1,200 requests per minute, described as dynamically adjusting.
- Context: 64k tokens for state plus all questions; 32k for state plus the longest question.
- Input: text only.
The response model field reports the versioned ID that actually answered, even if you sent an alias. Log it.
Pinning
If you have tuned confidence thresholds against a specific version, TypeSafe tells you to pin that versioned ID and move on your schedule. Aliases move when a release ships.
GET /v1/models currently lists aliases. Versioned IDs are still accepted on POST /v1/systemone whether or not they appear in the list.
Character of 1.13
TypeSafe’s own jaggedness summary: fast, calibrated, good at common-sense judgment; weaker on extra indirection, literal about wording, and unreliable at numeric precision. Details live on jaggedness.
Sources
Public TypeSafe or adjacent documentation only. No private claims.