Seedream 5.0 Pro API

Seedream 5.0 Pro is ByteDance's Doubao Seedream 5.0 Pro, released in July 2026. It handles text-to-image and single or multi-reference image-to-image with up to 10 reference images, and it renders text inside the image, which makes it a fit for posters and covers. Output comes in 1K, 1.5K or 2K tiers across 8 aspect ratios, one image per request. ByteDance also offers exact pixel sizes and a layer decomposition mode, but Jantaris does not expose those options yet.

Best for

• Event posters, book covers and album art with titles
• Brand key visuals built from product and style references
• Covers rendered in several aspect ratios from one prompt
• Ad variants that differ only in headline text

Prompting tips

• Put exact text in quotes and say where it goes and how it looks: "title 'NIGHT MARKET' across the top, bold sans-serif".
• Pick the tier with resolution (1K, 1.5K, 2K) and the frame with aspect_ratio; exact pixel sizes are not accepted on Jantaris.
• In multi-reference prompts, assign roles: "image 1 is the product, image 2 sets the color palette".
• Prompts can be up to 32,000 characters, so spell out every text block of a busy poster.

FAQ

How much does the Seedream 5.0 Pro API cost?

The rate is from $0.0783 per image. Failed requests are not charged. That includes an image blocked by the vendor's final content check: you get the full hold back, even though the generation already ran.

What resolutions does Seedream 5.0 Pro support?

1K, 1.5K and 2K tiers in 8 aspect ratios (1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9). Exact pixel sizes are not available in Jantaris yet.

Should I pick Seedream 5.0 Pro or Flash?

Pro targets poster-grade images with text. Seedream 5.0 Flash charges one price for every tier and takes the same 10 reference images.

How to call Seedream 5.0 Pro via API

curl https://jantaris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream-5.0-pro",
  "input": {
    "prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
    "aspect_ratio": "1:1",
    "resolution": "1K"
  }
}'

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": "seedream-5.0-pro",
    "input": {
        "prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
        "aspect_ratio": "1:1",
        "resolution": "1K"
    }
}).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": "seedream-5.0-pro",
    "input": {
      "prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
      "aspect_ratio": "1:1",
      "resolution": "1K"
    }
  }),
})).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/seedream-5.0-pro.