跳转到主要内容

​
路径参数

​
id
string
必填
初始图像生成请求返回的任务 ID。
如果创建响应中包含 poll_url，建议优先调用该特定 URL 进行轮询。某些图像任务可能会在 /v1/tasks/{id} 下显示 poll_url，而不是图像特定的状态路径。你也可以用 /v1/images/{id} 轮询 ldtask_... 这类公开图片任务 ID。这个兼容 alias 会复用与 /v1/images/generations/{id} 完全相同的鉴权、ownership 检查、计费 header、终态快照和响应形状。如果该任务已不存在或无法再从公开任务记录中查询到，TokenLab 会返回 async_task_not_found，并附带消息 Task not found or no longer available.

​
响应

​
created
integer
创建时的 Unix 时间戳。
​
task_id
string
任务标识符。
​
status
string
任务状态：pending、processing、completed 或 failed。
​
data
array
生成的图像数组（当 status 为 completed 时填充）。每个对象包含：
  • url (string): 生成图像的 URL
  • revised_prompt (string): 用于生成的提示词
​
error
string
错误信息（仅在 status 为 failed 时存在）。
curl "https://api.tokenlab.sh/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" \
  -H "Authorization: Bearer sk-your-api-key"

import requests

response = requests.get(
    "https://api.tokenlab.sh/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
    headers={"Authorization": "Bearer sk-your-api-key"}
)

data = response.json()
print(f"Status: {data['status']}")

if data["status"] == "completed":
    print(f"Image URL: {data['data'][0]['url']}")

const response = await fetch(
  'https://api.tokenlab.sh/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa',
  {
    headers: {
      'Authorization': 'Bearer sk-your-api-key'
    }
  }
);

const data = await response.json();
console.log(`Status: ${data.status}`);

if (data.status === 'completed') {
  console.log(`Image URL: ${data.data[0].url}`);
}

{
  "created": 1706000000,
  "id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "task_id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "poll_url": "/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "status": "pending",
  "data": [
    {
      "url": "",
      "revised_prompt": "a beautiful sunset over mountains"
    }
  ]
}

{
  "created": 1706000000,
  "id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "task_id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "poll_url": "/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "status": "completed",
  "data": [
    {
      "url": "https://cdn.example.com/generated/image-abc123.png",
      "revised_prompt": "a beautiful sunset over mountains with vibrant orange and purple colors"
    }
  ]
}

{
  "created": 1706000000,
  "id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "task_id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "poll_url": "/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "status": "failed",
  "error": "Content policy violation",
  "data": []
}

​
轮询最佳实践

建议轮询间隔：3-5 秒。大多数图像生成任务在 30-120 秒内完成，具体取决于模型和路由的提供商路径。
import requests
import time

def poll_image_task(task_id, api_key, max_wait=300, interval=3):
    """Poll for image generation result with timeout."""
    url = f"https://api.tokenlab.sh/v1/tasks/{task_id}"
    headers = {"Authorization": f"Bearer {api_key}"}

    start_time = time.time()
    while time.time() - start_time < max_wait:
        response = requests.get(url, headers=headers)
        data = response.json()

        if data["status"] == "completed":
            return data["data"][0]["url"]
        elif data["status"] == "failed":
            raise Exception(data.get("error", "Generation failed"))

        time.sleep(interval)

    raise TimeoutError(f"Task {task_id} did not complete within {max_wait}s")

# Usage
image_url = poll_image_task("ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa", "sk-your-api-key")
print(f"Generated image: {image_url}")