图片模型 API
Sunburst 适合需要精细构图和局部细节的图像创作。 参考图编辑 · NewRouters Images API
POST
/v1/tasksMODELgpt-image-2.6-sunburst代码示例与响应
/v1/tasks服务端调用
curl "https://newrouters.com/v1/tasks" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
--data '{
"model": "gpt-image-2.6-sunburst",
"input": {
"prompt": "把杯身改为蓝色，保留杯柄和背景。",
"size": "auto",
"quality": "low",
"output_format": "jpeg",
"images": [
"https://example.com/cup.png"
]
}
}'服务端调用
const apiBaseUrl = "https://newrouters.com";
const apiKey = process.env.API_KEY;
if (!apiKey) throw new Error("Set API_KEY in your server environment");
const response = await fetch(apiBaseUrl + "/v1/tasks", {
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": "Bearer " + apiKey
},
body: JSON.stringify({
"model": "gpt-image-2.6-sunburst",
"input": {
"prompt": "把杯身改为蓝色，保留杯柄和背景。",
"size": "auto",
"quality": "low",
"output_format": "jpeg",
"images": [
"https://example.com/cup.png"
],
"resolution": "2k"
}
})
});
const result = await response.json();
if (!response.ok) throw new Error(JSON.stringify(result));
console.log(result);服务端调用
import json
import os
from urllib.request import Request, urlopen
api_base_url = "https://newrouters.com"
api_key = os.environ["API_KEY"]
body = json.loads("{\"model\":\"gpt-image-2.6-sunburst\",\"input\":{\"prompt\":\"把杯身改为蓝色，保留杯柄和背景。\",\"size\":\"auto\",\"quality\":\"low\",\"output_format\":\"jpeg\",\"images\":[\"https://example.com/cup.png\"],\"resolution\":\"2k\"}}")
request = Request(
api_base_url + "/v1/tasks",
data=json.dumps(body).encode("utf-8"),
headers={
"Content-Type": "application/json",
"Authorization": "Bearer " + api_key
},
method="POST",
)
with urlopen(request) as response:
print(json.load(response))平台地址已填入，运行前设置 API_KEY 环境变量。示例不会自动发起请求。
202任务已受理
JSON
{
"id": "TASK_ID",
"status": "pending",
"model": "gpt-image-2.6-sunburst",
"result": null,
"error": null
}200成功结果
JSON
{
"id": "TASK_ID",
"status": "succeeded",
"model": "gpt-image-2.6-sunburst",
"result": {
"assets": [
"https://example.com/output.png"
]
},
"error": null
}- 创建任务01
POST /v1/tasks提交 model + input，保存返回的任务 id。
202 · pending - 轮询状态02
GET /v1/tasks/{id}pending / processing 时等待并继续查询。
等待 → 再查询 - 读取终态03
result.assets[] / error按任务终态读取对应结果。
succeeded→ assetsfailed→ error
Sunburst 适合需要精细构图和局部细节的图像创作。 在 NewRouters 使用型号 gpt-image-2.6-sunburst.
将可访问的原图 URL 放进 input.images。请把示例 URL 换成自己的图片，并在提示词中说明哪些细节需要保留。编辑结果可选 JPEG、PNG 或 WebP。
curl "https://newrouters.com/v1/tasks" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ --data '{ "model": "gpt-image-2.6-sunburst", "input": { "prompt": "把杯身改为蓝色，保留杯柄和背景。", "size": "auto", "quality": "low", "output_format": "jpeg", "images": [ "https://example.com/cup.png" ] }}'保存响应的任务 ID，使用同一个 Key 轮询 GET /v1/tasks/{id}。成功后从 result.assets 下载文件。