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

# Rate Limits

> Limits per endpoint, response headers, and retry patterns.

## Limits

| Endpoint                   | Rate limit       |
| -------------------------- | ---------------- |
| `POST /api/v1/chat`        | 60 req/min       |
| `POST /api/v1/search`      | 60 req/min       |
| `POST /api/v1/images`      | 30 req/min       |
| `POST /api/v1/video`       | 2 req/min        |
| `GET /api/v1/video/status` | Unlimited (free) |

## Response headers

Every response includes:

| Header                  | What it tells you              |
| ----------------------- | ------------------------------ |
| `X-RateLimit-Limit`     | Max requests in current window |
| `X-RateLimit-Remaining` | How many you have left         |
| `X-RateLimit-Reset`     | Seconds until window resets    |
| `Retry-After`           | Seconds to wait (only on 429s) |

## When you hit a limit

You get a `429` response:

```json theme={null}
{ "error": "rate_limit_exceeded", "message": "Rate limit exceeded" }
```

## Retry code

<CodeGroup>
  ```python Python — exponential backoff theme={null}
  import time, requests

  def call_with_retry(url, headers, json, max_retries=3):
      for attempt in range(max_retries):
          r = requests.post(url, headers=headers, json=json)
          if r.status_code == 200:
              return r.json()
          if r.status_code == 429:
              wait = int(r.headers.get("Retry-After", 2 ** attempt))
              time.sleep(wait)
              continue
          r.raise_for_status()
      raise Exception("Max retries exceeded")
  ```

  ```javascript Node.js — exponential backoff theme={null}
  async function callWithRetry(url, options, maxRetries = 3) {
    for (let i = 0; i < maxRetries; i++) {
      const r = await fetch(url, options);
      if (r.ok) return r.json();
      if (r.status === 429) {
        const wait = parseInt(r.headers.get("Retry-After") || 2 ** i);
        await new Promise(r => setTimeout(r, wait * 1000));
        continue;
      }
      throw new Error(`${r.status}: ${await r.text()}`);
    }
    throw new Error("Max retries exceeded");
  }
  ```
</CodeGroup>

## Tips

* **Space out batch requests** — add a small delay between calls instead of firing them all at once
* **Video polling doesn't count** — poll as often as you want (every 10s recommended)
* **Images have a lower limit** (30/min) because they're more expensive to generate
* **Video is 2/min** because each generation uses significant compute