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

# Budget

> Control agent costs with budget limits

Budget limits control how much your agents can spend.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Budget Control"
        A[🤖 Agent] --> U[💰 Usage]
        U --> B{Budget?}
        B --> |OK| C[✅ Continue]
        B --> |Exceeded| S[🛑 Stop]
    end
    
    classDef agent fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef ok fill:#10B981,stroke:#7C90A0,color:#fff
    classDef stop fill:#EF4444,stroke:#7C90A0,color:#fff
    
    class A,U agent
    class B,C ok
    class S stop
```

## Quick Start

<Steps>
  <Step title="Set Budget">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::Agent;

    let agent = Agent::new()
        .name("Assistant")
        .max_tokens(10000)  // Token limit
        .build()?;

    // Agent stops when limit reached
    ```
  </Step>

  <Step title="Track Usage">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    let response = agent.chat("Hello").await?;
    let usage = agent.usage();

    println!("Tokens used: {}", usage.total_tokens);
    println!("Estimated cost: ${:.4}", usage.estimated_cost);
    ```
  </Step>
</Steps>

***

## Budget Options

| Option         | Type    | Description                |
| -------------- | ------- | -------------------------- |
| `max_tokens`   | `usize` | Maximum tokens per session |
| `max_cost`     | `f64`   | Maximum cost in dollars    |
| `max_requests` | `usize` | Maximum API calls          |

***

## Related

<CardGroup cols={2}>
  <Card title="Telemetry" icon="signal" href="/docs/rust/telemetry">
    Usage metrics
  </Card>

  <Card title="Execution" icon="play" href="/docs/rust/execution">
    Execution limits
  </Card>
</CardGroup>