Edge Developer Platform
  • Pages
    • Product Introduction
    • Quick Start
      • Importing a Git Repository
      • Starting From a Template
    • Framework Guide
    • Project Guide
      • Project Management
      • edgeone.json
      • Error Codes
    • Build Guide
    • Deployment Guide
    • Domain Management
    • Pages Functions
    • KV Storage
    • Edge AI
    • EdgeOne CLI
    • Best Practices
      • 1-Minute Quick Deployment + Free Beta Test in Progress | Your Exclusive DeepSeek, Handled by EdgeOne!
      • Deploy WordPress Gatsby To EdgeOne Pages
      • Build an Ecommerce Platform Using WordPress + GatsbyJS
    • Migration Guides
      • Migrating from Vercel to EdgeOne Pages
      • Migrating from Cloudflare Pages to EdgeOne Pages
      • Migrating from Netlify to EdgeOne Pages
    • FAQs
    • Contact Us
    • Release Notes

1-Minute Quick Deployment + Free Beta Test in Progress | Your Exclusive DeepSeek, Handled by EdgeOne!

DeepSeek R1, a popular model with 70,000 stars on GitHub and over 4 million downloads on Hugging Face, is now free for edge deployment!

With EdgeOne Pages' "AI Chat Template", developers can build a dialogue-based AI website in just 1 minute. You can also explore more play modes - add an AI assistant to a technology blog, build a prototype of a knowledge library search for your team, experience zero-cost millisecond-level response of Edge AI, and start your intelligent project now!

The following video demonstrates the procedure of template deployment and how to use it:




Template Features and Advantages

Preset Deepseek-R1 model. No need for complex configuration. Just quickly launch.
Sink AI computing power to edge nodes, achieve lower delay and provide faster and smoother experience.
Can directly call AI model inside Pages Functions
Native support for OpenAI API standard APIs. The existing toolchain is plug-and-play.

Visit the demo site https://deepseek-r1-edge.edgeone.app to experience the ultimate speed of Edge AI, or log in to the EdgeOne Pages console for one-click deployment of your exclusive AI application.



Application Scenario Recommendations

Using this template, developers can try proof of concept in various scenarios. For example, they can quickly deploy an intelligent customer service system that seamlessly integrates with the enterprise official website, accurately interpret user inquiries, and automatically push operation guides, reducing the amount of manual handling of a large number of basic questions. It can also empower SaaS products to build an automation assistant, supporting high-frequency scenarios such as ticket categorization, data report interpretation, and business process configuration, helping users save time on repeated operations and achieve deep integration of AI capabilities with business flows.



Scenario-Based Integration Guide

Step 1: Click the link to directly enter the creation page https://console.tencentcloud.com/edgeone/pages/new?template=deepseek-r1-edge. Configure the project and then click "Create Now".


Step 2, after the project creation is successful, you will enter the deployment process. You can view the deployment procedure on the details page of build deployment.


Step 3. After successful deployment, click the domain for quick verification of the deployment achievement.


Step 4. Open the URL and send any question to DeepSeek R1. You will see very quick streaming output in response.


This is merely a simple Demo. You can also clone the code locally and update the project as you wish, such as adding new modules to enrich product capabilities.

In addition, our service goes directly from edge nodes to large models. It is an AI interface with a fully Serverless architecture and can be freely invoked without an API key.
// In an edge function (example path: /functions/v1/chat/completions/index.js)
export async function onRequestPost({ request }) {
// Parse user input
const { content } = await request.json();
try {
// Call the edge AI service
const response = await AI.chatCompletions({
model: '@tx/deepseek-ai/deepseek-r1-distill-qwen-32b',
messages: [{ role: 'user', content }],
stream: true, // Enable streaming output
});
// Return a streaming response
// ......
} catch (error) {
// ......
}
}

Since the project domain name has a validity period limit, we recommend that you add a custom domain name (such as www.example.com), so that the domain name can be used as a persistently callable API address.


API calls also meet the standard of Open AI API, which means you can easily switch among different AI providers and reuse existing code and tools.

The following code shows how to quickly integrate the service into your AI Business, realizing an automatic fault-tolerant failover mechanism among multiple AI providers, giving your business service elasticity with multi-protection.
export class AIService {
//......
constructor(
deepseekApiKey: string,
siliconFlowApiKey: string,
groqApiKey: string,
tencentApiKey: string
) {
// Initialize AI service configurations
this.serviceConfigs = [
// Add a new configuration item
{
name: 'edgeonepages',
baseURL: 'https://www.example.com/v1', // Replace www.example.com with your domain name
enabled: true,
priority: 1 // highest priority
},
{
name: 'tencent',
baseURL: 'https://api.lkeap.cloud.tencent.com/v1',
model: 'deepseek-v3',
enabled: true,
priority: 2 // second priority
},
{
name: 'deepseek',
baseURL: 'https://api.deepseek.com/v1',
model: 'deepseek-chat',
enabled: true,
priority: 3 // third priority
}
];
//......
}
}

The DeepSeek R1 AI Chat Template of EdgeOne Pages provides developers with the possibility of deploying AI applications on edge nodes. Although it is still in the early stage, it has shown huge potential. We sincerely invite developers to try out this template, experience DeepSeek R1 on edge nodes, and also feel the convenience and efficiency of Pages. We also look forward to your valuable feedback to help us continuously improve the experience of Pages.