Jev
- Price
- Paid
- API
- Yes
- Weights
- No
WHAT IT DOES
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.
WHY WE PICKED IT
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.
QUICK FACTS
STRENGTHS
- ✓New model class built for software decisions, not chat: typed probabilities in, not text
- ✓Claims 70-500ms responses and up to 193.6x faster, 444.6x cheaper than an equivalent LLM call
- ✓Cannot hallucinate by construction, since the output space is fixed in advance
- ✓Output tokens are free; input runs $0.042 per million tokens
- ✓Built by an ex-OpenAI ChatGPT researcher after two years in stealth
LIMITATIONS
- ⚠Early access only, gated behind a waitlist, no public self-serve signup yet
- ⚠All speed and cost multiples are TypeSafe's own published evals, not independently verified
- ⚠Not a general-purpose model: scoped to structured decisions defined in advance, so it can't replace an LLM for open-ended generation
- ⚠Too new for third-party benchmarks or production case studies to exist
GETTING STARTED
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.
OFFICIAL LINKS
SIMILAR TOOLS
PRICING
Requires a paid subscription.
FEATURED IN GUIDES
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 ...
EXPLORE ALTERNATIVES
Compare Jev with 5+ similar infrastructure AI tools.
FREQUENTLY ASKED QUESTIONS
Is Jev free?
No, Jev requires a paid subscription.
Does Jev have an API?
Yes, Jev offers an API for programmatic integration.
What is Jev best for?
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.
What platforms does Jev support?
Jev supports api.
Is Jev open source?
No, Jev is not open source.
How do I get started with Jev?
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.
FEATURED ON CURATEDAI
Work on Jev? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.
