Seedream 5.0 Pro API
Seedream 5.0 Pro is the China version of the Seedream 5.0 Pro image model: t2i creates images from text and i2i edits or restyles 1–10 reference images, producing one 1k or 2k image per request, billed in CNY.
Capabilities
- Model
- Image
- API model
seedream-v5-pro-i2i- Endpoints
- POST /v1/image/generations, GET /v1/image/generations/{id}
- Parameters
- prompt: 5–2000, images: 1–10 (i2i), metadata.resolution: 1k / 2k, metadata.width / metadata.height: 240–8192, ≤ 2048×2048 px, metadata.output_format: jpeg / png
Current pricing
seedream-v5-pro-i2i: ≈¥0.27–0.62 per request
Model variants
| API model | Use case | Current pricing |
|---|---|---|
seedream-v5-pro-i2i | Image editing | ≈¥0.27–0.62 per request |
seedream-v5-pro-t2i | Text to image | ≈¥0.27–0.53 per request |
Gallery examples
Abstract Lingzhi Fluid ArtAPI model:
seedream-v5-pro-t2iAbstract Lingzhi Fluid Art — explore this seedream-v5-pro-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Mystical Fantasy RealmAPI model:
seedream-v5-pro-t2iMystical Fantasy Realm — explore this seedream-v5-pro-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Poodle Among TulipsAPI model:
seedream-v5-pro-t2iPoodle Among Tulips — explore this seedream-v5-pro-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Tired Frog CommuterAPI model:
seedream-v5-pro-t2iTired Frog Commuter — explore this seedream-v5-pro-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Hallstatt Lake TownAPI model:
seedream-v5-pro-t2iHallstatt Lake Town — explore this seedream-v5-pro-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Pink Seaside CottageAPI model:
seedream-v5-pro-t2iPink Seaside Cottage — explore this seedream-v5-pro-t2i creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Quick start
Example workflow: create an e-commerce hero image with t2i, then switch to i2i and add images to change the scene or style. A prompt of 5–2000 characters is required; each reference may be up to 10 MB; t2i ignores images. metadata.resolution is 1k or 2k and takes priority over width and height; alternatively send metadata.width and metadata.height (240–8192 each, at most 2048×2048 pixels). output_format is jpeg or png. seed, n and ratio are not supported. The international versions, dola-seedream-5.0-pro-t2i / i2i, take the same parameters.
cURL
curl --fail-with-body https://www.zzai.app/v1/image/generations \
-H "Authorization: Bearer $SEEDANCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"images":["https://your-cdn.example/reference.png"],"metadata":{"output_format":"jpeg","resolution":"2k"},"model":"seedream-v5-pro-i2i","prompt":"A red ceramic teapot on a white table, soft morning light, product photography, no text."}'Python
import json, os, requests
payload = json.loads(r'''{"images":["https://your-cdn.example/reference.png"],"metadata":{"output_format":"jpeg","resolution":"2k"},"model":"seedream-v5-pro-i2i","prompt":"A red ceramic teapot on a white table, soft morning light, product photography, no text."}''')
response = requests.post(
"https://www.zzai.app/v1/image/generations",
headers={"Authorization": "Bearer " + os.environ["SEEDANCE_API_KEY"]},
json=payload, timeout=120,
)
response.raise_for_status()
print(response.json()["id"])JavaScript
const response = await fetch("https://www.zzai.app/v1/image/generations", {
method: 'POST',
headers: { Authorization: 'Bearer ' + process.env.SEEDANCE_API_KEY, 'Content-Type': 'application/json' },
body: JSON.stringify({"images":["https://your-cdn.example/reference.png"],"metadata":{"output_format":"jpeg","resolution":"2k"},"model":"seedream-v5-pro-i2i","prompt":"A red ceramic teapot on a white table, soft morning light, product photography, no text."}),
});
if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).id);Save the returned id as TASK_ID in the query example. Query every 3–5 seconds until success or failure; submission does not mean generation is complete. Save result files promptly. data.status: SUCCESS / FAILURE; data.result_url.
curl --fail-with-body https://www.zzai.app/v1/image/generations/$TASK_ID \
-H "Authorization: Bearer $SEEDANCE_API_KEY"Frequently asked questions
How do I call this model?
Create an API key, choose the model name below, and send a request to the documented OpenAI-compatible endpoint. Final billing follows the current price and usage parameters.