Why Choose EdgeOne Makers AI Agent Gateway
One ai api gateway for all your models — unified endpoint, full key management, SSE streaming, and 500K free tokens built in.
One Endpoint, All Models
Access DeepSeek, MiniMax, Hunyuan, OpenAI, Anthropic, Google and more through a single unified API endpoint — switch providers by changing one parameter.
Secure Key Management
Provider API keys are encrypted and hosted by the platform — your application only carries the gateway key, vendor secrets never touch client code.
Zero Platform Fee
The Models gateway service is completely free — no markup, no platform fees. You only pay for vendor API usage on their own platforms when using Bring-Your-Own-Key models.
Native SSE Streaming
All protocols and providers support Server-Sent Events streaming out of the box — real-time responses with OpenAI SDK, Anthropic SDK, or Vercel AI SDK.
How to Use the AI Agent Gateway in 3 Steps
Connect to the ai gateway and start calling models immediately — unified endpoint, single API key, zero configuration.
1
Get Your API Key
Sign up at the Makers console and create your gateway API key — one key for all model providers.
2
Point Your SDK
Set the base URL to the Makers gateway endpoint in your SDK — supports any OpenAI-compatible client.
3
Call Any Model
Send requests with your chosen `model` parameter — the gateway routes to the right provider automatically.
Complete AI Agent Gateway Features
Everything in the ai api gateway — unified endpoint, multi-provider access, key management, free tokens, and streaming support.
Feature | Description |
|---|---|
| Unified Endpoint | Single API endpoint for 8+ LLM providers — switch models by changing one parameter, no code changes |
| Multi-SDK Compatible | Works with OpenAI JS/Python SDK, Anthropic SDK, Vercel AI SDK, cURL, and any OpenAI-compatible client |
| Key Management | Provider keys encrypted and hosted — applications only carry the gateway API key |
| Built-in Models | Call models like `@makers/deepseek-v4-flash` without binding any provider key — free tokens included per account |
| SSE Streaming | Native Server-Sent Events support for all providers — real-time streaming with zero configuration |
What is the AI agent gateway on EdgeOne Makers?
The ai gateway is a unified model access service. It provides a single endpoint (`https://ai-gateway.edgeone.link/v1`) to call multiple LLM providers with one API key, compatible with OpenAI protocol.
Which model providers does the ai api gateway support?
The ai api gateway supports DeepSeek, MiniMax, Hunyuan, Zhipu, Moonshot, OpenAI, Anthropic, and Google AI Studio. Switch between providers by changing the `model` parameter — no code changes needed.
Is the ai gateway free to use?
Yes. New accounts receive 500K free tokens. Built-in models (like `@makers/deepseek-v4-flash`) can be called without binding any provider key. You can also bring your own API keys for additional models.
How does the ai gateway handle API key security?
The ai gateway provides full key management — provider keys are encrypted and hosted by the platform. Your application only carries the gateway API key, ensuring vendor keys never appear in client code.
Does the ai api gateway support streaming?
Yes. The ai api gateway natively supports Server-Sent Events (SSE) for all protocols and providers. Real-time streaming responses work out of the box with OpenAI SDK, Anthropic SDK, and Vercel AI SDK.