Docs
OfficialJev Guides & Articles
Models
The model card for jev-1.13.0: $42 per billion input tokens with free output, a 64k context, 250k tokens per second, and how to list the models your account can call.
- Format
- Docs
- Reading time
- 2 min
- Published by
- TypeSafe AI
- Last verified
- Sep 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- jev-latest and jev-preview both point at jev-1.13.0; there is no separate preview build.
- Output tokens are free; only input is billed, at $42 per billion tokens.
- 64k context covers 32k of state plus the longest question.
- Rate limits adjust dynamically and can change without notice.
Quickstart
python
from typesafe_sdk import TypeSafeClient
with TypeSafeClient() as client:
for model in client.models.list().models:
print(model.name, model.release_date, model.description)Watch out
English is the primary language and non-English accuracy is lower, so test before relying on it for other languages.
Questions about this entry
Short answers drawn from the linked project or page.
Nothing. The card says output tokens are free and only input is billed, at $42 per billion tokens, which is why adding questions to a request changes the bill far less than enlarging the state.
Not today. Both aliases point at jev-1.13.0 on the card, and the docs say jev-preview only moves ahead of jev-latest when a preview build is actually available. Pin a version ID in production so a release cannot shift your thresholds.
Every model is served by the same endpoint, POST /v1/systemone, and the request's model field selects which one handles the call.
A request over either the 100K-tokens-per-second or 80-requests-per-second limit returns 429 Too Many Requests; the client SDKs retry with backoff by default and honor the retry-after header when present.
No. It is not fine-tuned or LoRA-adapted with customer data; it is trained with RLCD to return calibrated decisions, and the same weights serve every account.
English is the primary training language and where accuracy is best; other languages including CJK scripts are handled but not equally well, so test on your own content and pay attention to confidence when routing.
The names your account can send in the model field, with a description and release date for each. It currently lists the aliases, though versioned IDs like jev-1.13.0 are accepted whether or not they appear.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: New signups no longer get free credits.
YouTube: Gary Explains the catch: Jev understands natural language but answers with structured values and confidence.
YouTube: David Ondrej explains the architecture behind Jev and how to build a business on it.
More Jev resources like this
TypeSafe AI's product site for Jev, its first System One Model: typed decisions with calibrated confidence, performance and pricing claims, a FAQ, and links to the docs, console, workflow evals, and launch post.
Jev Guides & ArticlesDocs#official#docs#models
Official
DeepInfra's reference for its hosted System One endpoint: POST /typesafe/v1/systemone takes a state, model, and questions and returns a model and answers, with a companion list-models endpoint.
Jev Guides & ArticlesDocs#community#docs#api
Community
OpenAI's API documentation page for Decisions, a hosted endpoint that returns bounded answers rather than generated text; the captured page is its header, pointing to the docs index at llms.txt.
Jev Guides & ArticlesDocs#community#openai#docs
Community
The enterprise page for Jev: two published case studies with 88% and 98.7% lower cost, SOC 2 Type II and zero data retention, a no-training-on-inputs commitment, and higher rate limits for teams.
Jev Guides & ArticlesDocs#official#enterprise#compliance
Official
The reply on TypeSafe's reopen thread: new Jev signups no longer receive free credits, and the console link is repeated.
Jev Guides & ArticlesPost#official#x#pricing
Official
A TypeSafe blog essay arguing that in ML the order that matters is doing the right task, then data, then compute, then algorithms, using the InstructGPT result as its example.
Jev Guides & ArticlesArticle#official#article#models
Official
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.