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

# Credits

> How usage is metered across RAIL endpoints, and what's free.

Scoring endpoints consume credits; reading your configuration and checking status are free. Your plan includes a monthly credit allowance, and each scored response reports its cost in a `credits_consumed` field.

<Info>
  Credits reset monthly and do not carry forward. Manage your plan and watch usage on the [dashboard](https://responsibleailabs.ai/dashboard).
</Info>

## What's free

These endpoints never consume credits:

| Endpoint                         | Purpose                                         |
| -------------------------------- | ----------------------------------------------- |
| `GET /railscore/v1/config`       | See your application's policy and configuration |
| `GET /railscore/v1/dimensions`   | The RAIL dimensions and your weights/thresholds |
| `GET /railscore/v1/capabilities` | Features and limits for your plan               |
| `POST /verify`                   | Validate a key and view your identity           |
| `GET /health`                    | Service status                                  |

Cached scoring results also return at no cost.

## What's metered

Scoring work is metered by how much analysis it does. Approximate costs:

| Operation              | Relative cost                                    |
| ---------------------- | ------------------------------------------------ |
| Evaluation, basic mode | Lowest                                           |
| Evaluation, deep mode  | Higher (more detailed analysis)                  |
| Safe regeneration      | Per evaluation + per rewrite, up to 5 iterations |
| Compliance check       | Per framework evaluated                          |
| Agent checks           | Low, per call                                    |

Evaluating a subset of dimensions costs proportionally less than scoring all eight. The exact `credits_consumed` is always returned on the response, and live per-plan pricing is shown on the [dashboard](https://responsibleailabs.ai/dashboard).

## Monthly allowance

| Plan       | Credits / month |
| ---------- | --------------- |
| Free       | 100             |
| Pro        | 1,000           |
| Business   | 10,000          |
| Enterprise | Custom          |

If you run out, a scoring request returns **HTTP 402** with your current balance and the amount required. Upgrade or request a top-up to continue.

## What's next

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/getting-started/quickstart">
    Make your first scored request.
  </Card>

  <Card title="Configuration" icon="gear" href="/api-reference/config">
    Inspect the policy governing your application.
  </Card>

  <Card title="Evaluation" icon="magnifying-glass" href="/concepts/evaluation">
    Basic vs deep mode, dimensions, and custom weights.
  </Card>

  <Card title="Dashboard" icon="chart-line" href="https://responsibleailabs.ai/dashboard">
    Watch usage and manage your plan.
  </Card>
</CardGroup>