Jepela documentation

Plain Markdown pages, the same ones /llms.txt lists for coding agents.

• Introduction Jepela 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
• Getting started in five minutes Jepela is a hosted API at `https://api.jepela.com`; you need only a key. Everything below was run for real; your numbers will differ a little.
• Quick start Jepela is a hosted API at `https://api.jepela.com`. There is nothing to install or run. Three steps.
• Examples Every request on this page was sent to a Jepela gateway on 2026-09-23 and every answer came back from it (`jepela-english` unless the request names a model). Th
• Jepela versus Jev Jev is TypeSafe AI's System One model, served at `api.typesafe.ai`. Jepela is this API. The request and answer shape is the same on purpose, so code written for
• State 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 Three question types, one request. Each is evaluated on its own against the same state.
• Choice Select one option from a defined set. The answer has the chosen option, a probability for every option, and a confidence.
• Score Rate the state against ordered levels. The answer has a score, a probability per level, the legend, and a confidence.
• Noul 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 Choice and Score answers carry `probabilities`, the full distribution, and `confidence`, one number from 0 to 1 that says how concentrated that distribution is.
• Request options Options on `POST /v1/systemone` beyond `state`, `questions`, `model` and `subject`. Each says what it costs.
• Warnings 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
• Memory 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.
• Rules in memory 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 decid
• Quality Jepela 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 questi
• Fine-tuning Train a Jepela model of your own on your labelled cases. It is used only if it answers cases it never saw better than the standard engine and still listens to m
• Batches Many decisions as one background job: a backlog to classify, a nightly re-scoring, a golden set of your own.
• Patterns Code owns the control flow. Jepela appears where the code needs a judgment. Four patterns from stateless decision APIs, then two that exist because of the memor
• Cookbooks End-to-end recipes in `cookbooks/`, each a Python script that runs against your gateway with `JEPELA_API_KEY` set and prints what it measured. The outputs below
• Models `GET /v1/models` lists what this gateway offers, whether each engine answers right now, and what is pinned.
• API reference Base URL: `https://api.jepela.com` (the API of your key's region; see Regions). Every `/v1` route except sign-up needs `Authorization: Bearer <key>`, and every
• Pricing 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 p
• Regions Jepela runs in regions. Each region is a whole Jepela: the API, every subject's memory and the GPU engine, in the same
• Python SDK `jepela-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 `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 direc
• Claude and MCP Jepela ships as an MCP server and a Claude Code plugin, so Claude can make typed decisions with memory as tool calls.
• Agent skill For Claude Code and other coding agents: a skill file, `SKILL.md`, tells an agent what Jepela is, when to use it inside the software it writes, and the exact re
• FAQ **Is Jepela 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,
• Troubleshooting Every error is JSON: `{"error": {"type": "...", "message": "..."}}`. The message says what to fix.
• Jaggedness What Jepela 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 Jepela checkpoints