> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apimart.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Development Guide

> Integrate the API into your application

# Development Guide

This guide helps you integrate our API services into your application.

## Asynchronous Processing

Our API uses an asynchronous processing model:

1. Submit a task: send a generation request and receive a task ID
2. Poll status: periodically check task status
3. Get results: fetch generation results when the task completes

### Polling example

```python theme={null}
import time
import requests

def wait_for_completion(api_key, task_id, max_wait=300):
    """Poll the task until it completes"""
    url = f"https://api.apimart.ai/v1/tasks/{task_id}"
    headers = {"Authorization": f"Bearer {api_key}"}
    start_time = time.time()

    while time.time() - start_time < max_wait:
        data = requests.get(url, headers=headers).json()["data"]
        status = data["status"]

        if status == "completed":
            return data["result"]
        elif status in ("failed", "cancelled"):
            raise Exception(f"Task {status}: {data.get('error')}")

        time.sleep(2)  # wait 2 seconds before polling again

    raise Exception("Task timeout")
```

## Error Handling

### Common errors

| Status | Description                | Resolution                          |
| ------ | -------------------------- | ----------------------------------- |
| 400    | Invalid request parameters | Check request parameters and format |
| 401    | Authentication failed      | Verify your API key                 |
| 402    | Insufficient balance       | Top up your account balance         |
| 429    | Rate limit exceeded        | Reduce request frequency            |
| 500    | Server error               | Retry later                         |

### Example

```python theme={null}
import requests

response = requests.post(
    "https://api.apimart.ai/v1/images/generations",
    headers={"Authorization": f"Bearer {api_key}"},
    json={"model": "gpt-4o-image", "prompt": "a cute panda"},
)

if response.status_code != 200:
    error = response.json().get("error", {})
    if response.status_code == 401:
        print("Invalid API key")
    elif response.status_code == 402:
        print("Insufficient account balance")
    else:
        print(f"Error: {error.get('message')}")
```

## Best Practices

1. Caching: generated image/video links are valid for 24 hours
2. Retries: implement exponential backoff on transient errors
3. Monitoring: regularly check API usage and quotas
4. Security: keep your API key secure

## Support

If you run into issues during development, you can get help via:

* Email: [zhihong@apimart.ai](mailto:zhihong@apimart.ai)
* Live chat: visit our website
* Docs: browse the full API documentation