Skip to main content

TypeSafe AIAdded Sep 18, 2026DecisionsAnonymizedBeta

Jev (System One)

Jev (System One) is TypeSafe AI’s decision model. Instead of writing text, it answers typed questions about a passage with structured judgments: yes-or-no probabilities, choices with confidence, or scores on a rubric. It reads up to 32,000 tokens of context, with up to 64,000 tokens across context and questions.

jev-latestPOST https://api.venice.ai/api/v1/decisions
Input / output
$0.042 / Free
per 1M tokens
Max state
32K
tokens
Max total
64K
tokens per request

Pricing

USD per 1M tokens
State tokens in
$0.042
Decision tokens out
Free

Specs

Model ID
jev-latest
Endpoint
POST /api/v1/decisions
Max state
32,000 tokens
Max total
64,000 tokens
Privacy
Anonymized
Added
Sep 18, 2026
POST/api/v1/decisions
curl https://api.venice.ai/api/v1/decisions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "jev-latest",
"state": "Help! My payouts have been failing for 3 days.",
"questions": {
"is_urgent": { "type": "noul", "instructions": "Does this need a reply within the hour?" }
}
}'