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

# Rate Limits

> Understand request limits by plan and how to handle rate limit errors.

## Rate Limits by Plan

| Plan       | Open-Source RPD | Closed-Source RPD | Pro Models RPD |
| ---------- | --------------- | ----------------- | -------------- |
| Free       | 150             | 70                | 0              |
| Starter    | 2,000           | 1,000             | 0              |
| Pro        | 4,500           | 2,500             | 650            |
| Enterprise | Unlimited       | Unlimited         | Unlimited      |

RPD = Requests Per Day

## Model Classes

| Class             | Examples                                |
| ----------------- | --------------------------------------- |
| **Open-Source**   | Llama, Mistral, Mixtral, DeepSeek, Qwen |
| **Closed-Source** | GPT-4o, Claude, Gemini, Grok            |
| **Pro**           | Sora, Veo, DALL-E 3 HD, gpt-4.5         |

## Rate Limit Headers

Every API response includes headers showing your current usage:

```http theme={null}
X-RateLimit-Limit-Requests: 2000
X-RateLimit-Remaining-Requests: 1847
X-RateLimit-Reset-Requests: 2024-01-01T00:00:00Z
```

## Handling Rate Limit Errors

When you hit a rate limit, the API returns HTTP `429`:

```json theme={null}
{
  "error": {
    "type": "rate_limit_exceeded",
    "message": "Rate limit exceeded. You have used 2000/2000 requests today.",
    "code": 429
  }
}
```

## Retry with Exponential Backoff

```python theme={null}
import time
import random
from openai import OpenAI, RateLimitError

client = OpenAI(
    api_key="sk-samurai-YOUR_KEY",
    base_url="https://api.samuraiapi.in/v1"
)

def chat_with_retry(messages, max_retries=5):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model="gpt-4o",
                messages=messages
            )
        except RateLimitError as e:
            if attempt == max_retries - 1:
                raise
            wait = (2 ** attempt) + random.random()  # Exponential backoff
            print(f"Rate limited. Retrying in {wait:.1f}s...")
            time.sleep(wait)
```

<Note>
  Rate limits reset at midnight UTC. Contact support for enterprise rate limit increases.
</Note>