Z-Image Pro API

Z-Image Pro is a text-to-image option from Alibaba's Z-Image family. On Jantaris it takes exactly two fields, prompt and seed, so everything about the frame has to be in the description. Each request returns one image, and there is no image input. The vendor also offers custom width and height and prompt rewriting, but Jantaris does not expose those options yet. It responds best to one dense English paragraph of about 90-170 words rather than a short list of tags.

Best for

• Character and location concepts for games or music videos
• Reproducible series built on a fixed seed
• Photoreal scenes described in one detailed paragraph
• Backgrounds for covers where you add text in an editor

Prompting tips

• Write a single paragraph of 90-170 English words covering subject, setting, light, lens and mood.
• Set seed to a fixed number to reproduce a result; 0, null or leaving it out gives a random seed.
• Change one phrase at a time while keeping the seed, so you can see what each word does.
• For fast, cheap drafts, Z-Image Turbo is the lighter option.

FAQ

How much does Z-Image Pro cost?

The rate is $0.05 per image. Failed generations are not charged, and the prepaid balance has no expiry date.

Can I set the image size in Z-Image Pro?

Not on Jantaris yet. The model supports custom width and height, but this channel takes only prompt and seed. If you need a specific ratio, use Z-Image Turbo, which offers 5 aspect ratios.

Does Z-Image Pro accept reference images?

No. It is text-to-image only, one image per request.

How to call Z-Image Pro via API

curl https://jantaris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "z-image-pro",
  "input": {
    "prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm"
  }
}'

import os, time, requests

API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}

task = requests.post(f"{API}/generate", headers=H, json={
    "model": "z-image-pro",
    "input": {
        "prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm"
    }
}).json()
while task["status"] in ("queued", "running"):
    time.sleep(3)
    task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()

print(task["status"], task["cost"], [o["url"] for o in task["output"]])

const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };

let task = await (await fetch(`${API}/generate`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "z-image-pro",
    "input": {
      "prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm"
    }
  }),
})).json();

while (task.status === "queued" || task.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));

Parameters

The same schema is available from GET /v1/models/z-image-pro.