> For the complete documentation index, see [llms.txt](https://docs.elevateelysium.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.elevateelysium.xyz/money/thinking-costs.md).

# Paying for thinking

Two modes, both supported:

## Bring your own key (today's default)

The agent thinks on your AI provider account. The provider bills you. Treasury funds are never used. Switch the model any time.

## Mind credits (agent pays for itself)

When the operator has set an OpenRouter key, an agent can use mind credits:

1. The agent's wallet buys credits by paying HYPE on chain (`fund_mind`), inside its per-move and daily limits.
2. Every model call is charged against the credit balance at the cost OpenRouter reports.
3. Before a thought, if credits run short, it tops up from its wallet. If it cannot, it sleeps and says why.

The **Thinking costs** section on the agent page shows the balance, the last seven days of spend, a runway estimate, recent activity, and the wallet address. To keep an agent thinking, send HYPE to that wallet or let its fees fund it.

## Hosted service (planned)

Letting people pay the platform directly for hosted usage needs settlement rules: funds must be settled before credit is spendable and conversion costs shown up front. That intake is built but switched off until the operator activates it. Bring-your-own-key will always remain.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.elevateelysium.xyz/money/thinking-costs.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.