Quickstart

Go from zero to your first generated image in three steps. The same flow works for video, audio and tool models.

1. Create an API key

Sign in with Google, top up your balance, and create a key from the API Keys page in your dashboard. Keys are shown only once — store them securely. Every key is prefixed with zk_task_.

2. Submit a task

Send a POST request with the model name and an input object describing what you want to generate.

bash

curl -X POST https://api.zekron.tech/api/v1/task \
  -H "Authorization: Bearer zk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zekron-image-pro",
    "input": {
      "prompt": "a red fox in a snowy forest, cinematic",
      "aspect_ratio": "16:9"
    }
  }'

The response returns a task in the queued or processing state:

json

{
  "id": "zk_task_8f3a2b1c9d",
  "status": "processing",
  "model": "zekron-image-pro",
  "created_at": "2026-06-10T12:00:00Z"
}

3. Poll for the result

Retrieve the task until its status becomes succeeded, then download the output URL.

bash

curl https://api.zekron.tech/api/v1/task/zk_task_8f3a2b1c9d \
  -H "Authorization: Bearer zk_live_xxx"

json

{
  "id": "zk_task_8f3a2b1c9d",
  "status": "succeeded",
  "output": {
    "images": ["https://cdn.zekron.tech/out/8f3a2b1c9d.png"]
  },
  "cost_usd": 0.018
}

Prefer not to poll? Pass a webhook_urlwhen creating the task and ZekronAI will call you when it finishes. See Polling & webhooks.