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

# Auto-Mode API

> Auto-Mode eliminates the guesswork from model selection by automatically choosing the optimal AI model for each query. 

# How Auto-Mode Works

### **Content Analysis**

Auto-Mode examines multiple dimensions of your request:

* **Code Detection**: Programming keywords, syntax patterns, language mentions
* **Mathematical Content**: Equations, formulas, calculation requests
* **Creative Requests**: Story writing, artistic content, imaginative tasks
* **Complexity Assessment**: Technical depth, reasoning requirements, context length
* **Query Type**: Simple questions vs. complex multi-step analysis

Each model in our ecosystem has a **detailed capability profile**. Auto-Mode weighs these capabilities against your query characteristics to find the optimal match!

# Using Auto-Mode

## Basic Usage

```javascript theme={null}
const response = await fetch('https://connectapi.answerr.ai/functions/v1/chat', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${YOUR_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: "auto",  // That's it!
    messages: [
      {
        role: "user",
        content: "Debug this Python function and explain what's wrong"
      }
    ]
  })
});
```

## When Auto-Mode Excels

### **Development Teams**

Auto-Mode is perfect for teams building diverse applications where different queries require different AI strengths. Instead of maintaining complex routing logic, let Auto-Mode handle the decisions while your team focuses on building features.

### **Customer Support**

Support tickets vary wildly—from simple FAQ responses to complex technical troubleshooting. Auto-Mode routes simple questions to fast, cost-effective models while escalating complex issues to premium models with stronger reasoning capabilities.

### **Educational Platforms**

Students ask questions across every subject imaginable. Auto-Mode sends math problems to models with strong quantitative reasoning, programming questions to code-specialized models, and essay assistance to models with creative writing strengths.

### **Content Creation Tools**

Whether users want technical documentation, creative stories, or marketing copy, Auto-Mode selects the model best suited for each creative task, optimizing both quality and cost.

### **Research Applications**

Academic and business research involves diverse query types—from data analysis to literature review to hypothesis generation. Auto-Mode adapts to each research phase automatically.

## **Business Benefits**

### **Cost Optimization**

Auto-Mode typically reduces API costs by 30-60% compared to always using premium models. It uses expensive models only when their capabilities are truly needed, routing simpler queries to more affordable options without sacrificing quality.

### **Performance Optimization**

By matching queries to each model's strengths, Auto-Mode often delivers better results than any single-model approach. Users get responses optimized for their specific needs rather than generic outputs.

### **Reduced Complexity**

No need to learn the nuances of each model, create routing logic, or maintain selection rules as models evolve. Auto-Mode handles all the complexity behind a simple parameter change.

### **Future-Proof Architecture**

As new models are added to the AnswerrAI ecosystem, Auto-Mode automatically incorporates them into its selection process. Your application benefits from new capabilities without code changes.

## Advanced Features

### Auto-Mode with Compare

Combine Auto-Mode with Compare functionality to see how the automatically selected model performs against alternatives:

```javascript theme={null}
{
  "model": "auto",
  "compareModel": "gpt-4o",
  "messages": [...]
}
```

This lets you validate Auto-Mode's selections and understand when manual model choice might be beneficial.

### **Selection Preferences**

Enterprise customers can customize Auto-Mode's selection criteria:

* **Cost-optimized**: Favor more affordable models when quality differences are minimal
* **Performance-optimized**: Prioritize response quality over cost considerations
* **Speed-optimized**: Prefer faster models for real-time applications
* **Custom weighting**: Define specific priorities for your use case

# Implementation Example

```javascript theme={null}
class AnswerrAI {
  constructor(apiKey) {
    this.apiKey = apiKey;
    this.baseURL = 'https://connectapi.answerr.ai/functions/v1';
  }

  async chat(messages, options = {}) {
    const response = await fetch(`${this.baseURL}/chat`, {
      method: 'POST',
      headers: {
        'Authorization': `Bearer ${this.apiKey}`,
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({
        model: options.model || 'auto',  // Default to Auto-Mode
        messages,
        temperature: options.temperature || 0.7,
        ...options
      })
    });

    const result = await response.json();
    
    // Log Auto-Mode selection for analytics
    if (result.model_selection) {
      console.log(`Auto-Mode selected: ${result.model}`);
      console.log(`Reasoning: ${result.model_selection.reasoning}`);
    }

    return result;
  }
}

// Usage
const ai = new AnswerrAI(process.env.ANSWERR_API_KEY);

// Auto-Mode handles model selection
const response = await ai.chat([
  { role: 'user', content: 'Explain quantum computing to a 10-year-old' }
]);
```

# Next Steps

Ready to implement intelligent model selection? Auto-Mode works with all AnswerrAI features:

* Compare Mode - Compare Auto-Mode selections with specific models
* File Analysis - Auto-Mode works with document and image analysis
* Sources & Suggestions - Enhanced responses with intelligent model selection

Start using Auto-Mode today by simply changing your model parameter to `"auto"`. Your applications will immediately benefit from optimized model selection without any additional integration work.