Overview
Makers Models is a unified model access service deployed on EdgeOne edge nodes, providing a one-stop invocation channel from client SDKs to large model providers. Developers can invoke large models from multiple mainstream providers through a unified endpoint and a single API Key, eliminating the need to carry provider-specific keys or to be compatible with multiple standard protocols. This helps you quickly build high-performance AI applications.
Core Capabilities
Unified Endpoint: Use a unified access address to invoke models from multiple providers. To switch models, simply modify the
model parameter.Multi-SDK/Protocol Compatibility: It is compatible with mainstream SDKs such as OpenAI SDK, Anthropic SDK, and Vercel AI SDK, and supports direct invocation by any HTTP client (cURL, fetch, and so on).
Full Key Hosting: When making calls, developers only need to carry the gateway's API Key. After their own provider keys are bound, the keys are encrypted and hosted by the platform.
Built-in Models Ready to Use: Built-in models are provided, which can be invoked without binding your own provider keys. This makes them suitable for quickly building applications and for technical validation.
Low Latency at Edge Nodes: Your service is deployed on the EdgeOne global edge network. Requests are processed locally and intelligently routed to various AI service providers.
Native Support for Streaming SSE: All protocols natively support Server-Sent Events (SSE) for streaming output.
Scenarios
AI Conversation and Streaming UI — Build conversational applications using any mainstream SDK. The frontend invokes calls through a backend proxy, and keys are not exposed on the frontend.
Flexible Multi-Provider Switching — This feature is suitable for scenarios that require quickly switching between different provider models based on business needs.
Demo and Prototype — This feature is suitable for scenarios such as early-stage developers needing to quickly build demonstration demos, for teaching purposes, or for technical validation.
Quick Start
Obtaining Makers Models API Key
1. Access the Makers console.
2. Log in to your account and activate Makers.
3. On the Makers / Models / API Key page, create an API Key.
4. Copy your API Key for use.
Calling Makers Models
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 osfrom openai import OpenAIclient = 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?"}]}'
MAKERS_MODELS_KEY=your-api-key-here
Note: Do Not Commit MAKERS_MODELS_KEY to Version Control.