# Jers > Jers is a decision API with memory: typed questions in, typed answers with probabilities out, one call, no text generation; a per-subject memory in RAM that the caller does not rebuild on every request; a subject is whatever a decision is about. You pay per input token the engine read, $0.042 per million; output is free. - [Introduction](https://us.api.getjers.com/docs/introduction.md): Jers is a decision API with memory. Send a state and typed questions; get typed answers with probabilities and confidence that your code can branch on. Name a subject, and the answer also uses what that subject's memory knows, without you packing it into every request. - [Getting started in five minutes](https://us.api.getjers.com/docs/getting-started.md): Jers is a hosted API at `https://api.getjers.com`; you need only a key. Everything below was run for real; your numbers will differ a little. - [Quick start](https://us.api.getjers.com/docs/quickstart.md): Jers is a hosted API at `https://api.getjers.com`. There is nothing to install or run. Three steps. - [Examples](https://us.api.getjers.com/docs/examples.md): Every request on this page was sent to a Jers gateway on 2026-09-23 and every answer came back from it (`jers-english` unless the request names a model). The answers are shortened: the decision id, the reading report, engine metadata, timings and most usage counters are left out, and a memory hit shows only its text; every field shown has its real name and place. Costs come from the gateway's `pricing.json`, placeholder prices until its owner sets them. Numbers will differ a little on your machine and with other checkpoints. Regenerate the page for your gateway with `python3 cookbooks/build_examples.py`. - [Jers versus Jev](https://us.api.getjers.com/docs/jers-vs-jev.md): Jev is TypeSafe AI's System One model, served at `api.typesafe.ai`. Jers is this API. The request and answer shape is the same on purpose, so code written for one runs against the other with a new base URL and a model name. Everything about Jev below is what TypeSafe's public pages said on 2026-09-22; their performance numbers are their claims. - [State](https://us.api.getjers.com/docs/state.md): The state is what the engine evaluates: a support message, a document, an application record. It goes in the `state` field next to the questions. - [Primitives](https://us.api.getjers.com/docs/primitives.md): Three question types, one request. Each is evaluated on its own against the same state. - [Choice](https://us.api.getjers.com/docs/choice.md): Select one option from a defined set. The answer has the chosen option, a probability for every option, and a confidence. - [Score](https://us.api.getjers.com/docs/score.md): Rate the state against ordered levels. The answer has a score, a probability per level, the legend, and a confidence. - [Noul](https://us.api.getjers.com/docs/noul.md): A yes/no statement. The answer is the probability that the answer is yes, with a `confidence` that is the larger of it and 1 minus it. - [Confidence](https://us.api.getjers.com/docs/confidence.md): Choice and Score answers carry `probabilities`, the full distribution, and `confidence`, one number from 0 to 1 that says how concentrated that distribution is. Concentrated on one outcome means a confident answer; spread out means an uncertain one. A Noul answer carries `noul` and `confidence`, the larger of `noul` and 1 − `noul`. - [Request options](https://us.api.getjers.com/docs/request-options.md): Options on `POST /v1/systemone` beyond `state`, `questions`, `model` and `subject`. Each says what it costs. - [Warnings](https://us.api.getjers.com/docs/warnings.md): Every answer carries `warnings`: known traps in this request, found by checks that cost nothing. The answer is returned either way; a warning says where it may be wrong. - [Memory](https://us.api.getjers.com/docs/memory.md): A memory is a list of lines that belongs to one subject of one tenant: facts, events your software reports, rules with conditions, decisions you choose to keep. It lives in RAM on Jers's server and is flushed to disk in the background. - [Rules in memory](https://us.api.getjers.com/docs/rules-in-memory.md): The memory is read by a one-pass decision engine, not a reasoner. Measured while building the demos and cookbooks with the English checkpoint, four things decide how a rule should be written. - [Quality](https://us.api.getjers.com/docs/quality.md): Jers tells you how often it is right on your own decisions, and tunes its confidence to them. Everything here works from labels: the right answer for a question, given after the fact. - [Batches](https://us.api.getjers.com/docs/batches.md): Many decisions as one background job: a backlog to classify, a nightly re-scoring, a golden set of your own. - [Patterns](https://us.api.getjers.com/docs/patterns.md): Code owns the control flow. Jers appears where the code needs a judgment. Four patterns from stateless decision APIs, then two that exist because of the memory. - [Cookbooks](https://us.api.getjers.com/docs/cookbooks.md): End-to-end recipes in `cookbooks/`, each a Python script that runs against your gateway with `JERS_API_KEY` set and prints what it measured. The outputs below are from runs on 2026-09-23, `jers-english` through a gateway and a product started by the build script from this repository; costs come from the gateway's `pricing.json`, placeholder prices until its owner sets them. Run `python3 cookbooks/build_docs.py` to regenerate this page for your gateway. - [Models](https://us.api.getjers.com/docs/models.md): `GET /v1/models` lists what this gateway offers, whether each engine answers right now, and what is pinned. - [API reference](https://us.api.getjers.com/docs/api.md): Base URL: `http://:8797`. Every `/v1` route except sign-up needs `Authorization: Bearer `, and every POST `Content-Type: application/json`. Bodies are capped at 1 MB (16 MB for `/v1/batches` and `/v1/golden`). Duplicate JSON keys are rejected. Connections stay open between requests (HTTP/1.1). - [Pricing](https://us.api.getjers.com/docs/pricing.md): You pay for input tokens: **$0.042 per million input tokens** (that is $42 per billion). Output is free. This is the same way TypeSafe prices Jev, at the same price. - [Regions](https://us.api.getjers.com/docs/regions.md): Jers runs in regions. Each region is a whole Jers: the API, every subject's memory and the GPU engine, in the same - [Python SDK](https://us.api.getjers.com/docs/sdk-python.md): `jers-sdk` 0.2 needs Python 3.10 or newer and nothing else; Pydantic is used only if you give it a Pydantic model. - [JavaScript and TypeScript](https://us.api.getjers.com/docs/javascript.md): `sdk/typescript` is a TypeScript client with no dependencies: it uses the `fetch` built into Node, Deno, Bun and browsers, and Node 22.18+ runs its source directly. Keep the key on your server; never ship it to a browser. - [Claude and MCP](https://us.api.getjers.com/docs/mcp.md): Jers ships as an MCP server and a Claude Code plugin, so Claude can make typed decisions with memory as tool calls. - [Agent skill](https://us.api.getjers.com/docs/agent-skill.md): For Claude Code and other coding agents: a skill file, `SKILL.md`, tells an agent what Jers is, when to use it inside the software it writes, and the exact request shape. Get it from [https://github.com/ceyoualigator-debug/getjers](https://github.com/ceyoualigator-debug/getjers) (`skills/jers/SKILL.md`) and copy it into `.claude/skills/jers/` of a project, or into `~/.claude/skills/jers/` for every project. The plugin brings a different skill, `jers-decisions`, for Claude's own tool calls. - [FAQ](https://us.api.getjers.com/docs/faq.md): **Is Jers a chat model?** No. It never generates text. You send a state and typed questions; you get typed answers with probabilities. Use it inside software, for judgments the code then acts on. - [Troubleshooting](https://us.api.getjers.com/docs/troubleshooting.md): Every error is JSON: `{"error": {"type": "...", "message": "..."}}`. The message says what to fix. - [Jaggedness](https://us.api.getjers.com/docs/jaggedness.md): What Jers gets wrong, as measured, so that you design around it rather than find out later. Measured on 2026-09-22 and 2026-09-23 with the Jers checkpoints on a Mac, unless a line says the engine's authors measured it. Other versions differ.