Seedream 5.0 Pro
Seedream 5.0 Pro text-to-image and image-to-image. Pass image_list to use reference images (up to 10), or omit it for pure text-to-image. Always returns a single image — this model does not support sequential (grouped) image generation.
Pricing: output is 2.25 tokens for 1K (= 0.090). Each reference image in image_list adds 0.15 tokens (= $0.0030). Example: 2K with 3 reference images = 4.5 + 3 × 0.15 = 4.95 tokens.
Returns an img_uuid; poll GET /api/v1/jobs/detail (or use custom_callback_url) to get the generated image.
Headers
Body
Text prompt describing the image.
1 - 2000Aspect ratio. Omit it to let the model pick from the prompt.
1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 Output quality tier. Only 1K and 2K are available for 5.0 Pro (5.0 Lite offers 2K/3K/4K).
1K, 2K Optional reference images for image-to-image, [{"url": "https://..."}]. Up to 10 images. Each one adds 0.15 tokens.
1 - 10 elementsOptional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.
"https://your-server.com/goenhance/callback"
