Guides
Concepts
The mental models: System One, the three primitives, state design, calibration, models & pricing, and the API reference.
Jev API Reference: Endpoint, Request Body & Response Shapes
The System One endpoint reference: POST api.typesafe.ai/v1/systemone, the state/model/questions body, per-primitive request and response shapes, 429 handling, and SDK installation.
Confidence & Calibration: When to Trust the Number
Jev returns probability (Noul) and probability + confidence (Choice/Score). What each field means, what calibration is, and how to design confidence gates that fall back to humans or LLMs.
Models & Pricing: jev-1.13.0, Costs, Limits & Honest Benchmarks
The Jev model card: jev-1.13.0 / jev-latest / jev-preview, $0.042 per million input tokens with free output, 64k context, rate limits, latency — plus the accuracy caveats nobody should skip.
State Design: State Is Not a Prompt
Jev's state field is a case file for an expert, not a chat prompt. Filter in code first, name fields so questions can point at them, and keep irrelevant detail out — it measurably degrades accuracy.
What Is a System One Model? Jev vs LLMs, Precisely
System One is the model category TypeSafe AI claims Jev opens: fast, calibrated, judgment-only. The four concrete differences from LLMs, the RLCD training method, and the "not just a classifier" debate.
The Three Primitives: Noul, Choice & Score
Every Jev question is one of three primitives — Noul (yes/no probability), Choice (1 of up to 255 options), Score (2–10 level rating). Full comparison table, selection guide, and the consistency traps.