How do I make my first Jev call?

Send one POST to TypeSafe's API with two fields: a state, which is the text to judge, and a questions object, where each question has a type of choice, score or noul and its instructions. The response comes back typed, with a probability for each option and a confidence, in 70 to 500 milliseconds.

No. It is one HTTP request, so curl or fetch is enough. TypeSafe also ships Python and JavaScript SDKs that add retries with backoff when you go over a rate limit, and there are integrations for LangChain, Pydantic AI, LiteLLM, OpenRouter and the Cloudflare and Netlify gateways.

How many questions can one call hold?

Enough that people ask 61 in a single request. Jev answers every question in parallel against the same state, so a long rubric costs about the same as one question. The limits that do bite are 64k tokens per request, 32k for the state plus the longest question, and 255 options in a single choice.

What do I do with the confidence score?

Pick a threshold and act on the answers above it automatically, escalating the rest to a person or a larger model. The probabilities say which option Jev picked; the confidence says how sure it is, and it is the number your code should branch on.

How do I use Jev with Claude Code or Cursor?

Either install the TypeSafe agent skill with npx skills add typesafe-ai/skills, so the agent writes programs that call Jev, or run an MCP server so the agent can ask Jev directly as a tool call.

How to use Jev

One POST request, two fields. You send the text and the questions you want answered about it; Jev sends back a typed answer, a probability for every option and a confidence score, in 70 to 500 milliseconds. Everything else on this page is what to do with that.

Updated 22 Sept 2026 · by Made with Jev

In short

Get an API key from TypeSafe, then send one request. No SDK required.
A call has a state (the text) and questions (choice, score or noul). All of them are answered in parallel.
Branch on the confidence, not the probability. That is the whole pattern.
For a coding agent: install the skill with npx skills add typesafe-ai/skills, or run an MCP server.

Step 1: one request

This is a whole Jev call. The state is what you want judged. Each key under questions is one question: a choice picks one of your options, a noul returns the probability that a statement is true, and a score places the state on a scale you define.

Request · POST /v1/systemone

{
  "state": "Thanks for the refund. Still annoyed it took three emails.",
  "model": "jev-latest",
  "questions": {
    "sentiment": {
      "type": "choice",
      "instructions": "The overall sentiment of this message",
      "criteria": {
        "positive": "Satisfied or thankful overall",
        "mixed": "Both satisfied and unhappy",
        "negative": "Unhappy overall"
      }
    },
    "needs_follow_up": {
      "type": "noul",
      "instructions": "A human should reply to this message"
    }
  }
}

Response

{
  "sentiment": {
    "choice": "mixed",
    "probabilities": { "mixed": 0.79, "negative": 0.2, "positive": 0.01 },
    "confidence": 0.61
  },
  "needs_follow_up": { "noul": 0.83 }
}

One thing catches everyone out: the question’s key, such as needs_follow_up, never reaches the model. Write the whole question in instructions, and write each criterion as the description of a bucket rather than as a label.

Step 2: branch on the confidence

The probabilities tell you what Jev picked. The confidence tells you how much weight the alternatives still carry, and that is the number your code should read. Above your threshold, act. Below it, hand the case to a person or to a larger model. Every production build in this directory has this shape somewhere in it.

What the answer is for

const { sentiment, needs_follow_up } = await jev(state, questions);

// Act on the sure ones; send the rest somewhere that can think.
if (sentiment.confidence < 0.7) return escalate(message);

if (needs_follow_up.noul > 0.8) return queueForHuman(message, sentiment.choice);

return file(message, sentiment.choice);

Where the threshold goes is an empirical question about your data, not a default. TypeSafe’s confidence docs explain how the score is produced.

Step 3: ask more questions, not more calls

Jev answers every question in a call in parallel against the same state, so the marginal cost of another question is close to nothing. Rob Hallam asks 61 questions about one draft post in about a second for $0.0004. The instinct to send one question per request is the most expensive mistake you can make with this model.

When the option list is the problem rather than the question count, the skill-suggestion cookbook shows the standard workaround: score everything in one pass, then run a second call over the shortlist. TypeSafe’s own Wikiracing demo picks links the same way, because a choice holds at most 255 options.

Endpoint: One POST, JSON in and JSON out
Latency: 70 to 500 ms, whatever the question count
Price: $0.042 per million input tokens; output free
Context: 64k per request; 32k for state plus longest question
Rate limits: 250,000 tokens a second, 1,200 requests a minute
Input: Text only: a string, a JSON object or a list of strings

Source: TypeSafe models and the quickstart. The same figures, with the evals, are on what is Jev.

Calling it from where you already are

You do not have to hold a TypeSafe key to use Jev. It is served through the gateways and framework integrations most stacks already have, which is also the quickest way to try it against a model you are currently paying for.

Route	Why you would use it
Jev on OpenRouter	One key across models you already call
Jev on Cloudflare AI Gateway	At the edge, with Workers
Jev on Netlify AI Gateway	Through Netlify's gateway
Jev through LiteLLM	Behind the LiteLLM proxy
Jev in Pydantic AI	Typed calls from Pydantic AI
langchain-typesafe	The LangChain integration package
Trace every judgment with Phoenix	Tracing each judgment in Phoenix

Using Jev from a coding agent

Two ways, and they are not the same thing. The agent skill teaches Claude Code or Codex to write programs that call Jev — install it with npx skills add typesafe-ai/skills, and the skills page lists the others people have published. An MCP server instead lets the agent ask Jev for a judgment while it works, as a tool call; those are on the Jev MCP page.

Watch someone do it

30 walkthroughs, tutorials and tests, all playable here. Start with Greg Isenberg’s if you want the shortest path to a working call, or the full tutorials below it if you would rather watch a whole build.

Guideyoutube.com/@GregIsenberg

Common questions

How do I make my first Jev call?: Send one POST to TypeSafe's API with two fields: a state, which is the text to judge, and a questions object, where each question has a type of choice, score or noul and its instructions. The response comes back typed, with a probability for each option and a confidence, in 70 to 500 milliseconds.
Do I need an SDK?: No. It is one HTTP request, so curl or fetch is enough. TypeSafe also ships Python and JavaScript SDKs that add retries with backoff when you go over a rate limit, and there are integrations for LangChain, Pydantic AI, LiteLLM, OpenRouter and the Cloudflare and Netlify gateways.
How many questions can one call hold?: Enough that people ask 61 in a single request. Jev answers every question in parallel against the same state, so a long rubric costs about the same as one question. The limits that do bite are 64k tokens per request, 32k for the state plus the longest question, and 255 options in a single choice.
What do I do with the confidence score?: Pick a threshold and act on the answers above it automatically, escalating the rest to a person or a larger model. The probabilities say which option Jev picked; the confidence says how sure it is, and it is the number your code should branch on.
How do I use Jev with Claude Code or Cursor?: Either install the TypeSafe agent skill with npx skills add typesafe-ai/skills, so the agent writes programs that call Jev, or run an MCP server so the agent can ask Jev directly as a tool call.

Made with Jev is independent and not affiliated with TypeSafe AI. Every figure on this page is the one its author published, linked to where it can be checked.

In short

Step 1: one request

Step 2: branch on the confidence

Step 3: ask more questions, not more calls

Calling it from where you already are

Using Jev from a coding agent

Watch someone do it

What to read next

Common questions