Jev 1.13

typesafe/jev-1.13
New
by TypeSafe · 2026-09-24

TypeSafe's structured decision and evaluation model. Give it a state and a set of named questions (noul / choice / score) and it returns a structured answer for each. Served via POST /v1/systemone; non-streaming; up to ~64K input tokens; text in, structured JSON out.

ctx65K tokens
Inputtext
Outputtext
p50 TTFT185 ms
INPUT$0.04/ 1M tokens
OUTPUT/ 1M tokens
p50 TTFT185 ms7d
p95 TTFT211 ms7d
TRAFFIC2.7Ktokens / 7d

Jev 1.13 is TypeSafe's structured decision and evaluation model. You send a state to judge plus a set of named questions, and Jev returns a structured answer for each — built for consistent,…

What is Jev 1.13?

Pricing

Pricing
Input / 1M tokens$0.042
Output / 1M tokens
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $0.294

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000001

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
185 ms
Output speed
35.9 tok/s
p95 TTFT
211 ms
Error rate
0%

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News3 mentions · 7dup 3 vs the previous week

FAQ

How is Jev different from a chat model?
Jev is a structured decision model, not a chat model. You provide a state (the material to judge) and a set of named questions; it returns one structured answer per question. It is called through a dedicated /v1/systemone endpoint rather than Chat Completions, and responses are not streamed.
What kinds of questions can I ask?
Three types. noul: a true/false judgment. choice: pick one of up to 255 labelled options. score: rate on an ordered scale of 2 to 10 levels. Each question carries its own instructions and (for choice/score) its criteria.
What is the input limit?
Roughly 64K tokens across the combined state and all questions. Requests over the limit are rejected before reaching the model.
Does it stream?
No. Jev returns a single structured response; there is no streaming mode.
What does it cost?
Pricing is configured per deployment and can be per-call or per-token. See the pricing on this page for the current rate.

Embed this badge

TypeSafe: Jev 1.13$0.04/M in185ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/typesafe/jev-1.13" target="_blank"> <img src="https://www.orcarouter.ai/embed/typesafe/jev-1.13.svg" alt="TypeSafe: Jev 1.13 on OrcaRouter" /> </a>
Markdown [![TypeSafe: Jev 1.13](https://www.orcarouter.ai/embed/typesafe/jev-1.13.svg)](https://www.orcarouter.ai/models/typesafe/jev-1.13)

Model card as data

GET /api/public/models/typesafe/jev-1.13Open
Machine-readable:/llms.txt/llms-full.txt