Back
All TypeSafe AI models
INFRASTRUCTURE • CURATED • UPDATED SEP 20, 2026

Jev

A System One Model: typed probabilistic decisions for software, not text for people

Jev is TypeSafe AI's first System One Model, published September 18, 2026 by former OpenAI researcher Diogo Almeida after two years in stealth. It is not an LLM and does not generate text: it takes application state and a structured question and returns a typed, calibrated probability that software can act on directly, what the company calls 'a frontier-intelligence function call.' It uses parallel sampling to produce the whole output at once instead of token-by-token, trained with a method TypeSafe calls Reinforcement Learning for Calibrated Decisions (RLCD). Because the output space is fixed in advance, TypeSafe says it cannot hallucinate. Published workflow evals claim 70-500ms response times and up to 193.6x faster, 444.6x cheaper results than equivalent-intelligence LLM calls on structured decision tasks.

Pricing Paid
Platforms api
API Yes
Open Source No
Modalities Infrastructure
Best For Best for Typed Decisions Inside Software Automation
Date Added 2026-09-20

It's a genuinely new model class rather than another chat model: built for the automation gap the founder points at directly, 'models have been superhuman at chat for years, so where is all the automation?' The catch is that every multiple above is TypeSafe's own published eval, it's gated behind an early-access waitlist with no public self-serve signup yet, and it only helps if your problem is a bounded decision, not open-ended generation.

Join the early access waitlist at typesafe.ai. There is no public self-serve API yet; TypeSafe is onboarding through the waitlist, with a Python wrapper and web console referenced in early documentation.

TypeSafe AI Introducing System One Models & Jev
Vercel LangSmith Pinecone Supabase Modal
Paid

Requires a paid subscription.

📚

RAG, Done Properly: Why Chunks Are the Wrong Unit of Knowledge

Chunk-based RAG retrieves text windows, not answers. On a 298-page benchmark, switching to question-...

Inference Engines Compared: llama.cpp, MLX, ExLlama, vLLM, SGLang, TensorRT-LLM

Inference engines are memory-bandwidth-bound schedulers, not just model loaders. Comparing llama.cpp...

How to Run an AI Agent Locally With Zero Token Costs

Perplexity and Nvidia just shipped a version of Perplexity's Computer agent that runs locally by def...

AI Infrastructure: Run, Host, or Rent?

Choosing AI infrastructure means trading control, cost, and latency against each other. Learn when t...

AI Infrastructure: Foundations at Scale

AI infrastructure is moving from "run models wherever" to specialized foundation layers. Understand ...

View Jev Alternatives (2026) →

Compare Jev with 5+ similar infrastructure AI tools.

Q

Is Jev free?

A

No, Jev requires a paid subscription.

Q

Does Jev have an API?

A

Yes, Jev offers an API for programmatic integration.

Q

What is Jev best for?

A

Jev is best for Typed Decisions Inside Software Automation. Jev is TypeSafe AI's first System One Model, published September 18, 2026 by former OpenAI researcher Diogo Almeida after two years in stealth. It's a genuinely new model class rather than another chat model: built for the automation gap the founder points at directly, 'models have been superhuman at chat for years, so where is all the automation?' The catch is that every multiple above is TypeSafe's own published eval, it's gated behind an early-access waitlist with no public self-serve signup yet, and it only helps if your problem is a bounded decision, not open-ended generation.

Q

What platforms does Jev support?

A

Jev supports api.

Q

Is Jev open source?

A

No, Jev is not open source.

Q

How do I get started with Jev?

A

Join the early access waitlist at typesafe.ai. There is no public self-serve API yet; TypeSafe is onboarding through the waitlist, with a Python wrapper and web console referenced in early documentation.

🏷️

Work on Jev? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.

Featured on CuratedAI