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

# Introduction

> Welcome to the Nano-GPT.com API

## Overview

The NanoGPT API allows you to generate text, images and video using any AI model available. Our implementation for text generation generally matches the OpenAI standards.

For API-key integrations, use `https://api.nano-gpt.com` as your API host. It accepts larger requests and allows longer-running requests than the website host, which matters for attachments and long model calls. See [API Hosts](/api-reference/miscellaneous/api-hosts) for SDK base URLs and the website flows that should stay on `nano-gpt.com`.

<Note>
  Partner domains such as [ai.bitcoin.com](https://ai.bitcoin.com), [bcashgpt.com](https://bcashgpt.com), and [cake.nano-gpt.com](https://cake.nano-gpt.com) may use the same API paths and request formats. Their request size and runtime limits can differ from `api.nano-gpt.com`.
</Note>

## Main API Endpoints

| Endpoint | Purpose |
| - | - |
| `POST /api/v1/chat/completions` | OpenAI-compatible chat generation |
| `POST https://api.nano-gpt.com/api/v1/batches` | Asynchronous Batch API jobs for Chat Completions and Responses requests |
| `POST /api/v1/responses` | OpenAI-compatible Responses API |
| `POST /v1/images/generations` | OpenAI-compatible image generation |
| `POST /api/generate-video` | Video generation, editing, extension, and upscaling |
| `POST /api/v1/messages` | Anthropic-compatible Messages API |

For selected endpoints, you can also use [Accountless x402 API Payments](/api-reference/miscellaneous/x402) to receive a payment quote without an account or API key by including `x-x402: true` on the initial unauthenticated quote request. Check `GET /api/v1/x402/endpoints` for the current supported matrix.

## Chat Completion example

Here's a simple python example using our OpenAI-compatible chat completions endpoint:

```python theme={null}
import requests
import json

BASE_URL = "https://api.nano-gpt.com/api/v1"
API_KEY = "YOUR_API_KEY"  # Replace with your API key

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
    "Accept": "text/event-stream"  # Required for SSE streaming
}

def stream_chat_completion(messages, model="minimax/minimax-m2.7"):
    """
    Send a streaming chat completion request using the OpenAI-compatible endpoint.
    """
    data = {
        "model": model,
        "messages": messages,
        "stream": True  # Enable streaming
    }

    response = requests.post(
        f"{BASE_URL}/chat/completions",
        headers=headers,
        json=data,
        stream=True
    )

    if response.status_code != 200:
        raise Exception(f"Error: {response.status_code}")

    for line in response.iter_lines():
        if line:
            line = line.decode('utf-8')
            if line.startswith('data: '):
                line = line[6:]
            if line == '[DONE]':
                break
            try:
                chunk = json.loads(line)
                if chunk['choices'][0]['delta'].get('content'):
                    yield chunk['choices'][0]['delta']['content']
            except json.JSONDecodeError:
                continue

# Example usage
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Please explain the concept of artificial intelligence."}
]

try:
    print("Assistant's Response:")
    for content_chunk in stream_chat_completion(messages):
        print(content_chunk, end='', flush=True)
    print("")
except Exception as e:
    print(f"Error: {str(e)}")
```

## Quick Start

The quickest way to get started with our API is to explore our [Endpoint Examples](/api-reference/endpoint/chat-completion). Each endpoint page provides comprehensive documentation with request/response formats and example code. The [Chat Completion](/api-reference/endpoint/chat-completion) endpoint is a great starting point for text generation.

## Documentation Sections

For detailed documentation on each feature, please refer to the following sections:

* [Text Generation](/api-reference/text-generation) - Complete guide to text generation APIs including OpenAI-compatible endpoints and legacy options
* [Image Generation](/api-reference/image-generation) - Learn how to generate images using various models like Recraft, Flux, and Stable Diffusion.
* [Video Generation](/api-reference/video-generation) - Create high-quality videos with our video generation API


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.