Home - TypeSafe AI
We took the opposite research direction
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.
193.6x Faster, 444.6x Cheaper.
*based on workflows for System One tasks (proof)
| Model | Cost | Time |
|---|---|---|
| TypeSafe AI | $0.000081 | 0.114s |
| LLMs | $0.013880 | 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.
| Model | Structured-output error rate | Tool-call error rate |
|---|---|---|
| Jev-1.0 | 0.00% | 0.00% |
| GPT-5.6 Luna | 0.49% | 14.3% |
| GPT-5.6 Terra | 0.58% | 5.41% |
| GPT-5.6 Sol | 1.93% | 22.1% |
| Claude Sonnet 5 | 12.6% | 3.03% |
| Claude Opus 5 | 3.76% | 0.34% |
| Claude Fable 5.1 | 7.99% | 0.80% |
| Gemini 3.8 Flash | 2.38% | 1.88% |
| Gemini 3.1 Pro | 1.92% | 2.64% |
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.
| Model | Input per million tokens | Output per million tokens |
|---|---|---|
| GPT-6 Astra | $10.00 | $50.00 |
| Claude Fable 5.1 | $10.00 | $50.00 |
| Claude Opus 5 | $5.00 | $25.00 |
| GPT-5.6 Sol | $4.00 | $20.00 |
| GPT-5.6 Terra | $2.00 | $12.00 |
| Claude Sonnet 5 | $2.00 | $10.00 |
| Claude Haiku 4.5 | $1.00 | $5.00 |
| GPT-5.6 Luna | $0.20 | $1.20 |
| Jev | $0.042 | Free |
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.
What is Jev good at? Where does it struggle?
Can Jev still get things wrong?