The ReqRun boundary
ReqRun is not a workflow orchestrator. It does not model arbitrary graphs, provider routing, or no-code workflows.
ReqRun focuses on making one OpenAI-compatible request durable, retryable, deduplicated, and observable.
How to use it safely
Call ReqRun at the point where your workflow or job needs an LLM request to finish or fail visibly.
import { ReqRun } from "@reqrun/sdk";
const reqrun = new ReqRun({
apiKey: process.env.REQRUN_API_KEY!,
signingSecret: process.env.REQRUN_SIGNING_SECRET!,
baseURL: "https://api.reqrun.com",
});
const result = await reqrun.chat.completions.create({
model: "gpt-5-nano",
messages: [{ role: "user", content: "Summarize this incident." }],
wait: true,
idempotency_key: "incident-421",
});