Skip to content
Jev Notes
English

TypeSafe · Jev AI notes

Jev AI by TypeSafe: answers with probabilities, not chat

Unofficial handbook for Jev AI by TypeSafe: System One returns typed answers with probabilities, not chat.

Last updated

API quickstartJev AI cases

This handbook covers the System One API, cost math, and when a decision model beats a chat LLM. See Jev AI cases and demos, the GitHub project directory, and the September 2026 channel map for jev-latest.

What Jev AI (TypeSafe) is for

Chat models generate words. The Jev AI model from TypeSafe returns typed decisions. The expensive part is not writing the reply. It is deciding what kind of work this is before you spend tokens on prose. System One is that first hop: classify, route, score, then hand off to code, a human, or a chat model.

Current public facts: context window 32,000 tokens; text-only input; model string jev-latest; input $0.042/M tokens with free output; claimed P50 around 0.23s. Vendor claims: 193.6x Faster and 444.6x Cheaper.

Three primitives

  • Noul: yes/no with a probability of yes.
  • Choice: pick one of up to 255 labeled options.
  • Score: ordered scale (2-10 levels) with a distribution.

Keys in the questions map are your names. Answers return under the same keys. Keys do not participate in reasoning. Batch many questions in one request. The cookbook claims 13 questions in one call can be about 12.2× cheaper and 10× faster than asking them separately.

30-second triage example

One System One call can ask several questions at once. The JSON below is an illustrative example from the TypeSafe docs, not a measured production run.

{
  "state": "Customer email: My invoice charged twice this month and I cannot download the PDF.",
  "model": "jev-latest",
  "questions": {
    "is_support": {
      "type": "noul",
      "instructions": "Is this a customer support request that needs a human or bot reply?"
    },
    "department": {
      "type": "choice",
      "instructions": "Route this message to the best department.",
      "criteria": {
        "billing": "Payments, invoices, refunds, subscriptions",
        "technical": "Bugs, outages, API errors, product failures",
        "sales": "Pricing questions, upgrades, new purchases"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "How urgent is a reply?",
      "criteria": [
        "low",
        "medium",
        "high"
      ]
    }
  }
}

Hard numbers (official claims)

  • 193.6x Faster · 444.6x Cheaper (TypeSafeAI 1.1 comparison on typesafe.ai)
  • Input $42 / billion tokens. Output free.
  • P50 latency about 0.23s. Context 32,000 tokens.
  • ~300 input tokens ≈ $0.0000126 per request.

Where teams actually use it

  • Support triage: noul for “needs human?”, choice for department, score for urgency, then confidence gates whether a bot replies or a ticket opens.
  • Agent routing: let a chat model draft, then ask Jev AI whether the draft is ready, on-policy, or should escalate.
  • Rubric judging: score or choice over fixed criteria when you need a distribution, not a paragraph of self-justification. OpenRouter traffic leaders include sel-jev-rubric-judge, Waura, mirasim, JeVinci, clara jev triage.

Naming rule on this site: say Jev AI or TypeSafe’s Jev AI in titles and first mentions. Prefer “Jev AI model” or “decision model” over bare “jev model”. The short form often collides with Japanese encephalitis virus and veterinary “animal model” results in English search.

How a production call usually looks

Keep API keys on a server. Send state (string, object, or array), set model to jev-latest, and pass a questions map. Prefer batching related questions in one HTTP request. Plan for 401 auth failure, 422 validation failure, 429 rate limit, and 529 overload. The last two should use exponential backoff. On OpenRouter, Jev AI rides the Decisions API, not chat completions.

instructions can also be structured data. Put the question in one field and keep references in sibling fields, then cite those fields with backticks inside the question text.

Architecture patterns worth copying

TypeSafe documents four composition patterns: speculative fan-out, confidence-gated routing, composite scoring, and intent routing. Most teams start with intent routing plus a confidence gate. Low confidence escalates. High confidence takes the cheap path.

Pairing models is normal. The chat LLM writes the customer-facing sentence. Jev AI decides whether that sentence should send, which template to use, or which queue owns the case.

What this handbook is not

We do not mirror the official docs page for page, we do not host TypeSafe branding, and we do not claim measured benchmarks unless we say so. Example JSON on this site is illustrative unless labeled otherwise.

The language button switches this handbook among English, Japanese, and Korean. Code samples stay as written.

Community cases

The Jev AI examples page lists 407 real builds and public demos, updated daily, with original text and a link back to each source.

Poster from Diogo Almeida (@CompleteSkeptic): After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led…Diogo Almeida @CompleteSkeptic · 34.6m viewsAfter co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth bui…Poster from tamara (@tamarajtran): found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compact…tamara @tamarajtran · 2.7m viewsfound the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it…Poster from Gregor Zunic (@gregpr07): Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 �…Gregor Zunic @gregpr07 · 2.5m viewsBreaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state…Poster from Matija Sosic (@MatijaSosic): Here's a 45-second TL;DR on Jev. I find the core idea beautifully simple, but the video ma…Matija Sosic @MatijaSosic · 1.4m viewsHere's a 45-second TL;DR on Jev. I find the core idea beautifully simple, but the video made it really hard to understand. Hope you find it…Poster from OpenRouter (@OpenRouter): Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai…OpenRouter @OpenRouter · 1.3m viewsIntroducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai The Jev Router picks the best model and reasoning…Poster from Vercel Developers (@vercel_dev): Jev by @typesafeai is free on Vercel AI Gateway until Sept 25. Build with the fastest adop…Vercel Developers @vercel_dev · 1.1m viewsJev by @typesafeai is free on Vercel AI Gateway until Sept 25. Build with the fastest adopted model on the Gateway at no cost. https://verce…

GitHub projects

The Jev GitHub projects page lists public repos that ship clients, agent guardrails, routers, and demos.

Call paths for jev-latest, Vercel AI Gateway, and OpenRouter are in the September 2026 channel map.

TypeSafe AI is the company that hosts the Jev model. Estimate a call on the pricing calculator. Recorded OpenRouter ids are on Jev AI on OpenRouter. Agent-skill repositories are grouped on Jev skills on GitHub.

JStypesafe-sdk-jstypesafe-ai/typesafe-sdk-jsOfficial TypeScript and JavaScript SDK with inferred answer types.ADadvocaatpithings/advocaatSmall type-safe client for asking Jev questions about datasets.AGagent-routernidhi-singh02/agent-routerPre-release Herdr integration that filters eligible coding models by quota and policy before Jev ranks them.DUduckdb-jevcolliber/duckdb-jevDuckDB extension that exposes Jev judgments as SQL values with return types derived from the declared criteria.JEjev-browserjkudish/jev-browserBrowser-use experiment powered by Jev decisions.FAfast-dev-compactionleonaaardob/fast-dev-compactionCodex port that restores Jev-selected verbatim history around native session compaction.

Tools on this site

A practical mental model

Treat Jev AI like a typed function, not a conversation partner. Prepare the state once, then ask several independent questions against that same state. Branch in code on the returned map. There is no assistant message to parse.

Batching keeps the decision layer cheap. Official cookbook numbers claim about 12.2× cheaper and 10× faster for 13 questions in one request versus asking them separately.

Confidence is the second control. Probability tells you how mass is distributed. Confidence tells you whether to act. Low confidence should escalate, not silently take the top option.

FAQ

Is Jev AI the same as TypeSafe AI?

No. TypeSafe AI is the company. Jev AI (System One) is their decision model. See the TypeSafe AI notes.

Is Jev Notes affiliated with TypeSafe AI?

Unofficial developer resource. Not affiliated with TypeSafe AI. We cite public docs. We do not sell access or imply a partnership.

Is this an OpenAI-compatible chat API?

No. System One is a Decisions API (https://api.typesafe.ai/v1/systemone). See the API quickstart.

Can Jev AI see images?

Not today. Input is text only: a string, a JSON object, or an array.

Does calibrated probability mean every answer is correct?

No. Official materials describe calibration over a population. Use confidence thresholds and human fallbacks for high-cost mistakes.

When should I still use a chat LLM?

Use a chat LLM when the artifact is language. Use Jev AI for the decision hop. See Jev AI vs LLM.

Where do I get an API key?

From the TypeSafe console at https://console.typesafe.ai. Keep keys on a server.

How do I estimate cost before integrating?

Use the pricing calculator. Public list price is $0.042/M input tokens. Output is free.

All 11 pages

  1. CasesReal Jev AI builds and public demos, updated when new community posts are added. Original text, metrics, and source links.
  2. TypeSafe AIWho TypeSafe AI is, founder Diogo Almeida, System One naming, published speed/cost claims, and official docs links.
  3. API quickstartPOST /v1/systemone with noul, choice, and score in one call. Auth, errors, backoff, and why chat-completions SDKs will not work.
  4. What is Jev AIJev AI is not a chat model. Learn noul, choice, score, confidence vs probability, and when not to use it.
  5. PricingEstimate daily and monthly cost at $0.042 per million input tokens. Output tokens are free. Compare against a chat LLM.
  6. PrimitivesField reference for noul, choice, and score plus a request builder that copies valid System One JSON.
  7. Jev vs LLMParallel sampling vs autoregression, latency, calibrated probabilities, and using LLM write + Jev judge together.
  8. ProjectsOfficial TypeSafe SDKs (Python/JS), 246 listed repos, featured stars and last push synced from GitHub, and skills listed.
  9. Jev as a judgePublic posts in this catalog that mention a judge, a rubric, or an eval, plus the score primitive and the sel-jev-rubric-judge traffic label stored here.
  10. OpenRouterRecorded OpenRouter model ids for Jev AI, the Decisions API warning, and prices stored in this handbook. Re-check the live card before you ship.
  11. Jev skillsAgent-skill repositories for Jev AI on GitHub, including the official skills repo when the catalog lists it, grouped by category.
Unofficial developer resource. Not affiliated with TypeSafe AI. Technical facts cite public TypeSafe and OpenRouter sources. Do not treat illustrative JSON as live benchmarks.