GPT Image 2.6 API
GPT Image 2.6 low-price creates and edits images with up to 16 references, one image per request at 1k, 2k or 4k, with a choice of the Flare or Sunburst version.
Capabilities
- Model
- Image
- API model
zhenzhen-image-g-v2.6-lowprice- Endpoints
- POST /v1/image/generations, GET /v1/image/generations/{id}
- Parameters
- prompt: 5–32000, images: 0–16, n: 1, size: auto / ratio, resolution: 1k / 2k / 4k, quality: auto / low / medium / high / xhigh / max, version: flare / sunburst, output_format: png / jpeg / webp / gif / svg, complexity: low / medium / high
Current pricing
¥0.04 per request
Gallery examples
The Bound TruthAPI model:
zhenzhen-image-g-v2.6-lowpriceThe Bound Truth — explore this zhenzhen-image-g-v2.6-lowprice creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Androgynous Dan HengAPI model:
zhenzhen-image-g-v2.6-lowpriceAndrogynous Dan Heng — explore this zhenzhen-image-g-v2.6-lowprice creation on OpenZhenZhen, with its original prompt and a reusable generation example.
My First ArtworkAPI model:
zhenzhen-image-g-v2.6-lowpriceMy First Artwork — explore this zhenzhen-image-g-v2.6-lowprice creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Snowy LandscapeAPI model:
zhenzhen-image-g-v2.6-lowpriceSnowy Landscape — explore this zhenzhen-image-g-v2.6-lowprice creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Amber Glass: Dual ProtagonistsAPI model:
zhenzhen-image-g-v2.6-lowpriceAmber Glass: Dual Protagonists — explore this zhenzhen-image-g-v2.6-lowprice creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Idol Stage PerformanceAPI model:
zhenzhen-image-g-v2.6-lowpriceIdol Stage Performance — explore this zhenzhen-image-g-v2.6-lowprice creation on OpenZhenZhen, with its original prompt and a reusable generation example.
Quick start
Example workflow: generate a white ceramic mug product shot with a size ratio, quality and resolution; add images (HTTP(S) or data URLs) to edit. The prompt is 5–32,000 characters; size accepts auto or a ratio, not WxH; quality is auto, low, medium, high, xhigh or max; version is flare (default) or sunburst. Note: a 1k, single-image, non-GIF/SVG request goes to the low-price route first, which keeps only the prompt, ratio, quality and references, so version, output_format and complexity have no effect; use 2k or 4k when you need them. GIF and SVG are text-only. output_compression, background, moderation and streaming are not supported.
cURL
curl --fail-with-body https://www.zzai.app/v1/image/generations \
-H "Authorization: Bearer $SEEDANCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"zhenzhen-image-g-v2.6-lowprice","n":1,"output_format":"png","prompt":"A white ceramic mug on a light grey table, soft daylight, product photography, no text.","quality":"high","resolution":"2k","size":"1:1"}'Python
import json, os, requests
payload = json.loads(r'''{"model":"zhenzhen-image-g-v2.6-lowprice","n":1,"output_format":"png","prompt":"A white ceramic mug on a light grey table, soft daylight, product photography, no text.","quality":"high","resolution":"2k","size":"1:1"}''')
response = requests.post(
"https://www.zzai.app/v1/image/generations",
headers={"Authorization": "Bearer " + os.environ["SEEDANCE_API_KEY"]},
json=payload, timeout=120,
)
response.raise_for_status()
print(response.json()["id"])JavaScript
const response = await fetch("https://www.zzai.app/v1/image/generations", {
method: 'POST',
headers: { Authorization: 'Bearer ' + process.env.SEEDANCE_API_KEY, 'Content-Type': 'application/json' },
body: JSON.stringify({"model":"zhenzhen-image-g-v2.6-lowprice","n":1,"output_format":"png","prompt":"A white ceramic mug on a light grey table, soft daylight, product photography, no text.","quality":"high","resolution":"2k","size":"1:1"}),
});
if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).id);Save the returned id as TASK_ID in the query example. Query every 3–5 seconds until success or failure; submission does not mean generation is complete. Save result files promptly. data.status: SUCCESS / FAILURE; data.result_url.
curl --fail-with-body https://www.zzai.app/v1/image/generations/$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.