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

# AI Tokens and Usage

> Understand how AI tokens work in UltraClaw. All plans include $15/mo in credits. Top up anytime.

# AI Tokens and Usage

Every interaction with your AI agent consumes **tokens** — the units that AI models use to process and generate text. UltraClaw handles all the complexity for you; all you need to know is how your credits work.

## What Are Tokens?

Tokens are the fundamental units AI models use to read and write text. A token is roughly **¾ of a word** — so a typical message might use a few hundred tokens for both your input and the agent's response.

You don't need to think about tokens directly. UltraClaw tracks everything and shows your usage in dollar terms on your dashboard.

## Included Credits

<Info>
  **All plans include \$15/mo in AI credits** — Starter, Pro, and Dedicated alike. This covers hundreds of typical messages per month.
</Info>

Your monthly credits reset at the start of each billing cycle. Unused monthly credits **do not roll over** to the next month.

## Top-Up Credits

Need more than your monthly allowance? Top up anytime:

* **$1 per $1 of credit**
* **Minimum purchase: \$10**
* **Top-up credits never expire** — they carry forward until you use them

Your agent always draws from monthly credits first. Top-up credits are only consumed after your monthly allowance runs out.

<Steps>
  <Step title="Open Your Dashboard">
    Go to [ultraclaw.ai/dashboard](https://ultraclaw.ai/dashboard) and navigate to **Billing**.
  </Step>

  <Step title="Click Top Up">
    Choose your top-up amount (\$10 minimum) and confirm payment.
  </Step>

  <Step title="Credits Applied Instantly">
    Your top-up balance appears immediately. Your agent is ready to go.
  </Step>
</Steps>

## What Affects Token Usage

Not all messages cost the same. Here's what influences consumption:

| Factor             | Impact                                                       |
| ------------------ | ------------------------------------------------------------ |
| **Message length** | Longer messages (yours and the agent's) use more tokens      |
| **Model choice**   | Some models cost more per token than others                  |
| **Thinking level** | Higher thinking levels use more tokens for deeper reasoning  |
| **Context window** | Conversations with more history loaded consume more per turn |
| **Integrations**   | Tool calls (calendar reads, email sends, etc.) add tokens    |

<Tip>
  Use the `/context` slash command to check your current token usage and see how much of the context window is being used.
</Tip>

## Monitor Your Usage

Your dashboard shows:

* **Current billing period usage** — how much of your \$15 monthly credit you've used
* **Top-up balance** — remaining purchased credits
* **Usage history** — daily and weekly breakdowns

<Warning>
  When both your monthly credits and top-up balance are exhausted, your agent will let you know it's time to top up. You won't be charged automatically — you stay in control.
</Warning>

## Tips for Efficient Usage

<CardGroup cols={2}>
  <Card title="Choose the Right Model" icon="sliders">
    Lighter models cost less per message. Use them for simple tasks and save premium models for complex reasoning. See [AI Models](/assistant/models).
  </Card>

  <Card title="Adjust Thinking Level" icon="brain">
    Lower thinking levels use fewer tokens. Use `/think off` for quick lookups and `/think high` only when you need deep analysis.
  </Card>

  <Card title="Compact When Needed" icon="compress">
    Long conversations accumulate context. Use `/compact` to summarize and free up tokens. See [Memory](/assistant/memory).
  </Card>

  <Card title="Keep Memory Curated" icon="broom">
    A bloated MEMORY.md file loads every session. Keep it focused on facts your agent actually needs.
  </Card>
</CardGroup>