# Claude AI

### Step-by-Step Token Generation 

#### 1. **Create Anthropic Account**

- Visit [console.anthropic.com](https://console.anthropic.com)
- Click **"Sign Up"** or **"Get Started"**
- Complete registration with email verification
- Log into the Anthropic Console dashboard

#### 2. **Access API Keys Section**

- Navigate to **"API keys"** in the left sidebar

#### 3. **Create New API Key**

- Click the **"Create API key"** button (or similar)
- A dialog box will appear with two simple fields:

#### 4. **Configure Key Settings**

- **Create in Workspace**: Select your workspace from dropdown 
    - Choose "Default" or your specific workspace
- **Name your key**: Enter descriptive name 
    - Example: "RoostGPT-Production", "Testing-Environment", etc.  
        [![Screenshot 2025-09-08 at 2.04.39 PM.png](https://docs.roost.ai/uploads/images/gallery/2025-09/scaled-1680-/w3VmNg7oKQnpNKvO-screenshot-2025-09-08-at-2-04-39-pm.png)](https://docs.roost.ai/uploads/images/gallery/2025-09/w3VmNg7oKQnpNKvO-screenshot-2025-09-08-at-2-04-39-pm.png)
- Click **"Add"** button

#### 5. **Secure Key Storage**

- **Copy immediately**: The full API key will be displayed once
- The key will start with `sk-ant-api03-` format

## Anthropic Claude Recommended Models for RoostGPT Integration

## **Claude Sonnet 4** (Primary Recommended)

- **Model Name**: `claude-sonnet-4-20250514`
- **Context Window**: 200K tokens (1M tokens available with beta header)
- **Max Output**: 64,000 tokens
- **Latency**: Fast
- **Training Data**: March 2025
- **Pricing**: $3/1M input tokens, $15/1M output tokens
- **Best For**: **Primary choice** for all RoostGPT tasks - optimal balance of performance, speed, and cost
- **Key Features**: 
    - High intelligence with balanced performance
    - Extended thinking capabilities for complex reasoning
    - Multimodal support (text and vision)
    - Large output capacity ideal for comprehensive code generation
    - Fast response times suitable for interactive development

## **Claude Opus 4.1** (Premium Alternative)

- **Model Name**: `claude-opus-4-1-20250805`
- **Context Window**: 200K tokens
- **Max Output**: 32,000 tokens
- **Latency**: Moderately Fast
- **Training Data**: March 2025
- **Pricing**: $15/1M input tokens, $75/1M output tokens
- **Best For**: Most demanding tasks requiring highest intelligence
- **Key Features**: 
    - Highest level of intelligence and capability
    - Most advanced extended thinking capabilities
    - Superior performance on complex engineering problems
    - Latest training data (most recent model)
    - Best choice for critical analysis and complex debugging

## **Claude Haiku 3.5** (Speed & Cost Optimized)

- **Model Name**: `claude-3-5-haiku-20241022`
- **Context Window**: 200K tokens
- **Max Output**: 8,192 tokens
- **Latency**: Fastest
- **Training Data**: July 2024
- **Pricing**: $0.25/1M input tokens, $1.25/1M output tokens
- **Best For**: High-volume, speed-critical tasks
- **Key Features**: 
    - Fastest response times in the Claude family
    - Intelligence at blazing speeds
    - Most cost-effective for bulk operations
    - Multimodal capabilities maintained
    - No extended thinking (optimized for speed)