After integrating Codex with Jev, my token quota consumption was reduced by 90%.

I actually tested inputting a single sentence:

“Should I buy a gaming console?”

Jev quickly classifies it as “purchase consultation,” with 97% probability and 0.96 confidence, then proceeds directly to subsequent processing.

It’s best suited for these tasks: classification, filtering, routing, quick judgments.

Codex continues to handle complex reasoning.

Integration is also very straightforward:

First, go to https://typesafe.ai to apply for the Waitlist. Once approved, create an API Key in the console, then have Codex execute:

npx skills add typesafe-ai/skills –skill typesafe-ai

After installation, simply add to the Prompt:

Use typesafe skill. Complex reasoning is handled by Codex; classification, filtering, routing, and simple judgments are prioritized to Jev, and specify which steps used Jev.

The actual experience boils down to four words: super fast, incredibly cost-saving!

Codex handles thinking, Jev handles high-speed judgments, and code handles flow control.

Home - TypeSafe AI

Source: https://typesafe.ai/

We took the opposite research direction

not chat

Reinforcement Learning from Human Feedback (RLHF) has led to LLMs that are optimized for human preferences. This has led to models that are superhuman at instruction following, and are what we now call “chat.” Yet RLHF creates inherent issues such as mode dropping, overconfidence, and lack of reliability. These flaws mean that LLMs require humans-in-the-loop.

a new model

We built a new class of models, System One Models, to be natively used by machines. We’re building with a new architecture, a new sampler, and a new training algorithm: Reinforcement Learning for Calibrated Decisions (RLCD).

Decisions, not strings

Typed outputs that software can act on.

calibrated confidence

Every decision includes an estimate of how confident the model is.

more like code

Reliable, fast, and type-safe.

[b.64]

ZmxvYXQgUV9yc3FydCggZmxvYXQgbnVtYmVyICkKewoJbG9uZyBpOwoJZmxvYXQgeDIsIHk7Cgljb25zdCBmbG9hdCB0aHJlZWhhbGZzID0gMS41RjsKCXgyID0gbnVtYmVyICogMC41RjsKCXkgID0gbnVtYmVyOwoJaSAgPSAqICggbG9uZyAqICkgJnk7CglpICA9IDB4NWYzNzU5ZGYgLSAoIGkgPj4gMSApOwoJeSAgPSAqICggZmxvYXQgKiApICZpOwoJeSAgPSB5ICogKCB0aHJlZWhhbGZzIC0gKCB4MiAqIHkgKiB5ICkgKTsKLy8JeSAgPSB5ICogKCB0aHJlZWhhbGZzIC0gKCB4MiAqIHkgKiB5ICkgKTsKCXJldHVybiB5Owp9

193.6x Faster, 444.6x Cheaper.

*based on workflows for System One tasks(proof)

TypeSafe AI

Cost $0.000081

Completed in 0.114s

LLMs

Cost $0.013880

Completed in 8.566s

Built for automation

Jev returns typed decisions with calibrated probabilities, so your software can account for uncertainty. Set the thresholds for when it acts autonomously and when it asks for review. Combine those decisions in code to build larger workflows, with control over how the intelligence is used.

Jev’s intelligence per dollar is literally off the charts.

Machine-Native Intelligence

LLMs produce words for people. Jev produces typed decisions and is more like code: reliable, fast, self-consistent, and type-safe.

Zero Hallucinations

Every Jev decision comes with a confidence estimate, so your software can act when confidence is high and escalate when it is not.

$42

Per Billion input tokens.

238x

Lower input price than Claude Fable 5.1

Come Build With Us

We give a FAQ

What are System One Models? What is Jev?

System One Models are a new class of AI model built for decisions inside software. Jev is TypeSafe’s first public System One Model, optimized for automation. Send Jev structured questions and get typed decisions with probabilities and confidence that your software can act on.

Is Jev just a smaller LLM?

How is this different from JSON mode or structured outputs?

How can Jev be so fast and inexpensive?

Can you make Jev even faster?

Are these prices temporary or subsidized?

What is Jev good at? Where does it struggle?

Can Jev still get things wrong?

How do I get started or ask a question?

[b.64]

iVBORw0KGgoAAAANSUhEUgAAABwAAAAcCAAAAABXZoBIAAAAl0lEQVR42mNgGPyg5u9/e1xyCV9+/7XDJVn/G7eky5vfl+U5sMvZPPn9Ow6XobP//t2LS07k7+/XTjjkFM7+/V2HS2PG7787+HHIBXz4fVAcl6F///6dj8vQ6b9//1bHIWdw9/fvNbg0vvr9+wgPLsm/v39H4pKb///vX3lcNj75+70HR4AzOPz+ewdn/OOVlDiIR5K6AACSCULwD4UI6QAAAABJRU5ErkJggg==

VHlwZVNhZmUgQUkgSW50ZWxsaWdlbmNlIE5vdw==

govin.eth | G哥 (@goan999999): Jev 这东西有点太tm离谱了

速度快 20～200 倍，成本低 40～400 倍

我把目前能找到的 Jev 项目翻了一遍，你能用到的都在这里👇

01｜jev-ultrafast

Browser Use 高速 Agent，Jev 负责每一步判断，Google Flights 完整搜索约 7.1 秒 https://t.co/EE0gCVq2Qf

02｜jev-desktop 把 Jev