Adding AI Image Generation to Your App

What you'll build

Submit an image prompt as an asynchronous task, check its status, and read the generated result. The exact input fields depend on the model you select.

1. Choose a model and create an API key

Browse the live image model catalog, open a model's detail page, and follow its request schema. Create an API key from Keys.

2. Submit a task

const headers = {
  Authorization: "Bearer " + process.env.ORUX_API_KEY,
  "Content-Type": "application/json",
}

const response = await fetch("https://orux.top/api/v1/tasks", {
  method: "POST",
  headers,
  body: JSON.stringify({
    model: "YOUR_IMAGE_MODEL_ALIAS",
    input: { prompt: "a red fox in a snowy forest, cinematic light" },
  }),
})

if (!response.ok) throw new Error(await response.text())
const { task_id } = await response.json()

Replace the model alias and input fields with values accepted by the model detail page.

3. Poll for the result

let task
do {
  await new Promise((resolve) => setTimeout(resolve, 5000))
  task = await fetch("https://orux.top/api/v1/tasks/" + task_id, { headers }).then((r) => r.json())
} while (task.status === "QUEUED" || task.status === "RUNNING")

if (task.status !== "SUCCESS") throw new Error(task.error?.message ?? task.status)
console.log(task.result)

Failed or expired tasks are not charged. Check current model prices and each model's supported settings before submitting.

Common API responses

• HTTP 401 — check that the API key is present, valid, and sent as a Bearer token.
• HTTP 402 — the account balance is insufficient; review the balance page.
• HTTP 429 — slow down requests and retry with exponential backoff and jitter.

Next steps

Compare image models in the catalog, try a model in its detail page, and use the API quickstart to review authentication.