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

# Rate Limits

> Understand Axon AI's rate limiting policies and tier-based quotas

Axon AI enforces rate limits to ensure fair usage and maintain system stability. These limits are applied per API key and are measured across a one-minute window.

## Rate Limit Tiers

Different service tiers offer varying rate limits to accommodate different usage patterns and requirements. Below are the rate limits for each tier:

| Tier    | Requests per Minute | Input Tokens per Minute | Output Tokens per Minute | Credits to Purchase | Max Monthly Spend |
| ------- | ------------------- | ----------------------- | ------------------------ | ------------------- | ----------------- |
| Default | 20                  | 30,000                  | 8,000                    | \$5                 | \$100             |
| Tier 2  | 200                 | 300,000                 | 80,000                   | \$40                | \$500             |
| Tier 3  | 400                 | 600,000                 | 160,000                  | \$200               | \$1,000           |

### Default Tier

The default tier provides basic rate limits suitable for most development and testing scenarios. This tier is unlocked with `$5` credits and has a maximum monthly spend of `$100`.

### Tier 2

Tier 2 offers 10x the default limits, ideal for production applications with moderate usage. This tier is unlocked with `$40` credits and has a maximum monthly spend of `$500`.

### Tier 3

Tier 3 provides the highest limits at 20x the default, designed for high-volume production workloads. This tier is unlocked with `$200` credits and has a maximum monthly spend of `$1,000`.

## Understanding Rate Limits

* **Requests per Minute**: The maximum number of API calls allowed per minute
* **Input Tokens per Minute**: The maximum number of tokens that can be sent as input per minute
* **Output Tokens per Minute**: The maximum number of tokens that can be generated as output per minute

**When a rate limit is exceeded, the API will return a 429 (Too Many Requests) status code.** Your application should implement appropriate retry logic with exponential backoff to handle rate limit errors gracefully.