Use the Jev API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/typesafe/system_one \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "jev-latest",
"prompt": "Route this support ticket to billing, technical, or sales, score customer frustration, and decide whether a refund was requested."
}'import { JevClient } from "@runapi.ai/jev";
const client = new JevClient();
const result = await client.systemOne.run({
model: "jev-latest",
prompt: "Route this support ticket to billing, technical, or sales, score customer frustration, and decide whether a refund was requested.",
});require "runapi/jev"
client = RunApi::Jev::Client.new
result = client.system_one.run(
model: "jev-latest",
prompt: "Route this support ticket to billing, technical, or sales, score customer frustration, and decide whether a refund was requested."
)npx skills add runapi-ai/jev -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorJev is TypeSafe's flagship System One model. Send it application state and structured questions; it returns typed answers with probabilities and confidence that your code can act on, without generating chat text.
| Model ID | jev-latest |
| Provider | TypeSafe |
| Modality | utility |
| Task type | synchronous |
| Billing unit | 1K tokens |
| API endpoint | /api/v1/typesafe/system_one |
| Commercial license | Yes — included via API |
| Catalog status | Operational |
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
Jev is built for automation, not chat. Through RunAPI, the Jev API uses one key and token billing alongside the rest of the catalog.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
Chat models generate text for people. Jev returns typed decisions, probabilities, and confidence that software can branch on, sort, and route with.
Classification, intent routing, scoring, extraction, guardrails, and other software decisions where handwritten rules are too brittle.
Choice picks one option from a set you define. Score rates the state against an ordered rubric. Noul answers a yes-or-no question with a probability.
Text only — a string, JSON object, or array. Pre-process images, audio, or video into text before sending them as state.
Use jev-latest. RunAPI maps it to the current TypeSafe Jev release.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.