# Jev Notes

> Unofficial developer notes for Jev AI — decisions, not chat.

Unofficial developer resource. Not affiliated with TypeSafe AI.

Site: https://jevnotes.com
Official docs (third party): https://docs.typesafe.ai
Official docs llms.txt: https://docs.typesafe.ai/llms.txt

## Pages

- [Jev AI: TypeSafe's System One Model That Returns Decisions, Not Text](https://jevnotes.com/): Developer notes for Jev AI: typed decisions with probabilities, not chat completions. Quickstart, primitives, pricing, and when to use a decision model.
- [TypeSafe AI: The Company Behind Jev (Founder, Funding, Docs)](https://jevnotes.com/typesafe-ai/): Who TypeSafe AI is, founder Diogo Almeida, System One naming, published speed/cost claims, and official docs links.
- [Jev API Quickstart: A Copy-Paste Python Example (jev-latest)](https://jevnotes.com/api-quickstart/): POST /v1/systemone with noul, choice, and score in one call. Auth, errors, backoff, and why chat-completions SDKs will not work.
- [What Is Jev AI? Noul, Choice and Score Explained](https://jevnotes.com/what-is-jev-ai/): Jev AI is not a chat model. Learn noul, choice, score, confidence vs probability, and when not to use it.
- [Jev Pricing Calculator: What $42 per Billion Tokens Costs You](https://jevnotes.com/pricing-calculator/): Estimate daily and monthly cost at $0.042 per million input tokens. Output tokens are free. Compare against a chat LLM.
- [Jev Primitives: Noul vs Choice vs Score (Full Field Reference)](https://jevnotes.com/primitives/): Field reference for noul, choice, and score plus a request builder that copies valid System One JSON.
- [Jev vs LLM: When a Decision Model Beats a Chat Model](https://jevnotes.com/jev-vs-llm/): Parallel sampling vs autoregression, latency, calibrated probabilities, and using LLM write + Jev judge together.