• Product Introduction
  • Quick Start
    • Agent Development
    • Importing a Git Repository
    • Starting From a Template
    • Direct Upload
    • Start with AI
  • Framework Guide
    • Agent
    • Frontends
      • Vite
      • React
      • Vue
      • Hugo
      • Other Frameworks
    • Backends
    • Full-stack
      • Next.js
      • Nuxt
      • Astro
      • React Router
      • SvelteKit
      • TanStack Start
      • Vike
    • Custom 404 Page
  • Project Guide
    • Project Management
    • edgeone.json
    • Configuring Cache
    • Building Output Configuration
    • Domain Management
      • Overview
      • Custom Domain
      • HTTPS Configuration
        • Overview
        • Apply for Free Certificate
        • Using Managed SSL Certificate
      • Configure DNS CNAME Record
    • Error Codes
  • Build Guide
  • Deployment Guide
    • Overview
    • Create Deploys
    • Manage Deploys
    • Deploy Button
    • Using Github Actions
    • Using Gitlab CI/CD
    • Using CNB Plugin
    • Using IDE PlugIn
    • Using CodeBuddy IDE
  • Enterprise Solutions
    • Vibe Coding
    • Platform and Multi-Tenancy
    • Internal Applications
  • Observability
    • Overview
    • Metric Analysis
    • Log Analysis
  • Functions
    • Overview
    • Edge Functions
    • Cloud Functions
      • Overview
      • Node.js
      • Python
      • Go
  • Agents
    • Overview
    • Quick Start
    • Conversation Management
    • Observability
    • Sandbox Tool
      • Overview
      • Using the Agent Framework
      • Sandbox Atomic API
      • Network Search Tool
    • Agent Authentication
  • Models
    • Overview
    • Models and Vendors
      • Overview
      • Using Vendor Keys
        • OpenAI
        • Anthropic
        • Google AI Studio
        • DeepSeek
        • MiniMax
        • Hunyuan
        • Zhipu
        • MoonShot AI
    • FAQs
  • Storage
    • Overview
    • KV
    • Blob
  • Middleware
  • AI-Native Development
    • Skills
    • MCP
  • Copilot
    • Overview
    • Quick Start
  • API Token
  • EdgeOne CLI
  • Message Notification
  • Integration Guide
    • AI
      • Makers Models Integration
      • Large Models for Images Integration
    • Database
      • Supabase Integration
      • Pages KV Integration
    • Ecommerce
      • Shopify Integration
      • WooCommerce Integration
    • Payment
      • Stripe Integration
      • Integrating Paddle
    • CMS
      • WordPress Integration
      • Contentful Integration
      • Sanity Integration
      • Payload Integration
    • Authentication
      • Supabase Integration
      • Clerk Integration
  • Best Practices
    • Adding an AI Chat Assistant to a Website
    • AI Dialogue Deployment: Deploy Project with One Sentence Using Skill
    • Building Agent Applications Quickly with Makers Agents
    • Building an Ecommerce Platform with Shopify
    • Building a SaaS Site Using Supabase and Stripe
    • Building a Company Brand Site Quickly
    • How to Quickly Build a Blog Site
    • Quick Launch via Login-Free Deployment in WorkBuddy
  • Migration Guides
    • Migrating from Vercel to EdgeOne Makers
    • Migrating from Cloudflare Pages to EdgeOne Makers
    • Migrating from Netlify to EdgeOne Makers
  • Troubleshooting
  • FAQs
  • Limits
  • Pricing
  • Contact Us
  • Release Notes

Makers Models Integration

Makers Models is a unified model access service deployed on EdgeOne edge nodes. With a gateway URL and an API Key, you can call multiple model providers and switch models by modifying the model parameter, without adapting to each provider's authentication method separately in your business code. This document describes how to create an API Key, select a model, integrate code, and perform local debugging and deployment.

Quick Start

1. Selecting a Project Type

Project Type
Key and Configuration Source
Agent project
Automatically configure model gateway variables during deployment.
Web project
Manually create an API Key in the Models console.
markdown To build an Agent project, we recommend starting with OpenAI Agents Starter. Click Deploy, connect your Git platform, and create a project. The platform then completes the build and deployment, so you do not need to manually create a Models API Key.

2. Selecting a Model Source

markdown Makers Models provides two model sources, but applications always use the Models API Key for authentication. Bound third-party provider keys are encrypted and hosted by the platform, so you do not need to write them into your business code.
Dimension
Built-in Model
Self-Funded Vendor Model (BYOK)
Preliminary Preparation
No vendor Key binding required
Bind the corresponding vendor API Key in the console.
Model ID
@makers/<model>
<provider>/<model>
Billing
Uses limited quota provided by Makers
Fees are charged to the developer's vendor account.
Scenarios
Demo, teaching, prototyping, and technical verification
Production environments and specified commercial models
markdown For details on built-in models and self-funded provider models, refer to Model and Provider Overview.

3. Configuring Environment Variables

markdown Go to the Makers console and choose ModelsAPI Key to create a Key. Create and securely store your Makers Models API Key:
MAKERS_MODELS_KEY=your-api-key-here
markdown Applications use the Makers Models API Key to access models. If you later integrate self-funded provider models, you only need to bind the provider API Key to the console. It is encrypted and hosted by the platform and should not be written into business code.

markdown Security note: API keys can only be stored in server-side environment variables. Do not write them into frontend code or logs, or commit them to Git repositories.

Calling Models

markdown The following example uses the built-in model @makers/deepseek-v4-flash. To call other models, simply replace the model parameter.
AI SDK
OpenAI JS SDK
Python
cURL
import { createAiGateway } from "@edgeone/makers-models-provider";
import { generateText } from "ai";

const aiGateway = createAiGateway({
apiKey: process.env.MAKERS_MODELS_KEY,
});

const { text } = await generateText({
model: aiGateway("@makers/deepseek-v4-flash"),
prompt: "What can you do?",
});
import OpenAI from "openai";

const client = new OpenAI({
apiKey: process.env.MAKERS_MODELS_KEY,
baseURL: "https://ai-gateway.edgeone.link/v1",
});

const completion = await client.chat.completions.create({
model: "@makers/deepseek-v4-flash",
messages: [{ role: "user", content: "What can you do?" }],
});
import os
from openai import OpenAI

client = OpenAI(
api_key=os.getenv("MAKERS_MODELS_KEY"),
base_url="https://ai-gateway.edgeone.link/v1",
)

completion = client.chat.completions.create(
model="@makers/deepseek-v4-flash",
messages=[{"role": "user", "content": "What can you do?"}],
)
curl -X POST "https://ai-gateway.edgeone.link/v1/chat/completions" \
--header "Authorization: Bearer $MAKERS_MODELS_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "@makers/deepseek-v4-flash",
"stream": true,
"messages": [{"role": "user", "content": "What can you do?"}]
}'

Switching Models

Switching Built-in Models

markdown Built-in model IDs start with @makers/. To switch models, you only need to modify the model ID:
const model = aiGateway("@makers/kimi-k2.6");
markdown The model list may be updated. We recommend that you copy the complete and currently available model ID from the console or Model and Provider Overview.

Switching to Self-paid Vendor Models

1. markdown Go to the Models page in the Makers console.
2. markdown Select a model provider and bind its API Key.
3. markdown Change model to <provider>/<model>, for example, anthropic/claude-sonnet-5.
4. markdown Keep the Makers Models gateway Key and Base URL unchanged.
5. markdown Redeploy after updating the environment variables or code.
markdown Note: The provider API Key is used by the Makers gateway to send requests to the provider. The application itself still uses the Makers Models gateway Key. The availability scope, regional restrictions, quotas, and billing rules of the provider's models are subject to the corresponding provider account.

Local Debugging and Deployment

1. Starting the Local Development Service

markdown After installing EdgeOne CLI, you can start and debug the project locally. If you need to use the environment variables configured in the Makers console, run edgeone makers link first to link an existing project.
edgeone makers dev
markdown The default access URL is http://localhost:8088/. For Agent projects, you can also access the local observability tracing page at http://localhost:8088/agent-metrics.

2. Deploying a Project

markdown If your project is connected to a Git repository, pushing code triggers the CI build and deployment in Makers. You can also deploy directly through the CLI:
markdown # Deploy to Production
edgeone makers deploy

ai-agent
You can ask me like
How to Get Started with EdgeOne Makers?