> ## 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.

# Getting Started with AnswerrAI API

> Unleash the power of multiple AI models through a single, elegant API.

## **Welcome to AnswerrAI**

The AnswerrAI API provides **unified access** to the world's leading AI models through a single, elegant interface. Instead of managing multiple API keys, learning different request formats, and juggling various providers, you get **one endpoint** that connects you to OpenAI, Anthropic Claude, Google Gemini, and more.

Whether you're building a chatbot, analyzing documents, or creating the next breakthrough AI application, AnswerrAI eliminates the complexity of multi-provider integration while unlocking advanced features like intelligent model selection and side-by-side comparisons.

# Quick Start

## 1. Get Your API Key

Sign up at [connect.answerr.ai](http://connect.answerr.ai) and grab your API key from the dashboard. You'll need this for all requests.

## 2. Make Your First Request

```javascript theme={null}
curl -X POST https://connectapi.answerr.ai/functions/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "user",
        "content": "Hello, world!"
      }
    ]
  }'
```

## 3. Get Your Response

```javascript theme={null}
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm here to help you with any questions or tasks you have. What would you like to know or discuss today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 28,
    "total_tokens": 37
  }
}
```

That's it! You just made your first AI request. The same endpoint works with any model in our ecosystem.

# Base URL

All API requests use this base URL:

```javascript theme={null}
https://connectapi.answerr.ai/functions/v1/chat
```

## Choosing Your AI Model

We've simplified model selection while giving you maximum flexibility. Access the latest and legacy models from:

| Name                  | Model Name               |
| --------------------- | ------------------------ |
| GPT-5                 | gpt-5                    |
| GPT-5 mini            | gpt-5-mini               |
| GPT-5 nano            | gpt-5-nano               |
| GPT-4.1               | gpt-4.1                  |
| GPT-4.1 mini          | gpt-4.1-mini             |
| GPT-4.1 nano          | gpt-4.1-nano             |
| OpenAI o3             | o3                       |
| OpenAI o3-mini        | o3-mini                  |
| OpenAI o4-mini        | o4-mini                  |
| GPT-4o                | gpt-4o                   |
| GPT-4o mini           | gpt-4o-mini              |
| Claude Sonnet 3.7     | claude-3-7-sonnet-latest |
| Claude Opus 4         | claude-opus-4-20250514   |
| Claude Sonnet 4       | claude-sonnet-4-20250514 |
| Claude Haiku 3.5      | claude-3-5-haiku-latest  |
| Gemini 2.5 Pro        | gemini-2.5-pro           |
| Gemini 2.5 Flash      | gemini-2.5-flash         |
| Gemini 2.0 Flash      | gemini-2.0-flash         |
| Gemini 2.0 Flash-Lite | gemini-2.0-flash-lite    |

Simply specify your model of choice in the request. No need to maintain multiple API keys or learn different request formats.

```javascript theme={null}
// OpenAI's GPT-4
{ "model": "gpt-4o", "messages": [...] }

// Anthropic's Claude
{ "model": "claude-3-5-sonnet", "messages": [...] }

// Google's Gemini
{ "model": "gemini-pro", "messages": [...] }

// Let AI choose the best model
{ "model": "auto", "messages": [...] }
```

Each model has unique strengths - OpenAI excels at coding and structured outputs, Claude shines with nuanced understanding of complex instructions, and Gemini offers exceptional reasoning capabilities.

## Streaming Responses

Get responses as they're generated for better user experience:

```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: 'claude-3-5-sonnet',
    messages: [{ role: 'user', content: 'Write a short story about AI' }],
    stream: true  // Enable streaming
  })
});

// Process the stream
const reader = response.body.getReader();
while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  
  // Handle each chunk of the response
  console.log(new TextDecoder().decode(value));
}
```

# Advanced Features

## Auto-Mode: Let AI Choose

Don't know which model is best for your task? Set `model: "auto"` and our intelligent routing will select the optimal model based on your query characteristics:

```javascript theme={null}
{
  "model": "auto",
  "messages": [
    {
      "role": "user", 
      "content": "Debug this Python function and explain what's wrong"
    }
  ]
}
```

## Compare Mode: See the Difference

Want to compare how different models handle the same request? Add a `compareModel` parameter:

```javascript theme={null}
{
  "model": "gpt-4o",
  "compareModel": "claude-3-5-sonnet",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ]
}
```

## Enhanced Responses

Add context and follow-up suggestions to your responses:

```javascript theme={null}
{
  "model": "gpt-4o",
  "messages": [...],
  "includeSources": true,      // Get web sources that support the response
  "includeSuggestions": true   // Get suggested follow-up questions
}
```

## What's Next?

Now that you've made your first request, explore the full capabilities:

* Chat Completions - Deep dive into the core API
* Auto-Mode - Learn about intelligent model selection
* Compare Mode - Compare models side-by-side
* File Analysis - Analyze documents, images, and code
* Sources & Suggestions - Enhanced responses with context

#