Overview
Makers Models provides two methods for invoking model services: built-in models and pay-as-you-go vendor models.
Built-in Models
Makers Models provides a selection of built-in models. Additionally, we offer a support program for scenarios such as early-stage developers and technical validation, which includes free, limited usage of built-in models. Our aim is to provide you with growth support from zero to one through technology democratization, thereby lowering the development barrier for AI applications.
The following are the available models:
@makers/hy3@makers/hy3-preview@makers/deepseek-v4-pro@makers/deepseek-v4-flash@makers/minimax-m3@makers/minimax-m2.7@makers/kimi-k2.6Note:
1. The purpose of the built-in model service is to provide technical validation for early-stage AI application scenarios. It does not guarantee the quality of model outputs. Do not use it in production environments.
2. When the system service detects high-frequency abnormal calls, persistent resource consumption in non-real business scenarios, or other suspected violations (such as commercial abuse or black/gray market activities), it may trigger an automatic protection mechanism. This mechanism imposes rate limiting or feature restrictions on the abnormal accounts.
3. If an account is in arrears, the model service is terminated immediately.
4. You can view the free quota and model usage on the Models page in the console.
Usage Methods
The model name for a built-in model must include the
@makers/ prefix. For example, to invoke @makers/deepseek-v4-flash: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?"}]}'
Note:
The model ID in the model parameter must exactly match the one in the table above.
Vendor Models for Self-Payment
Makers Models supports proxy forwarding to multiple mainstream model vendors. Developers can bind a vendor's API Key on the Models page in the console. After successfully binding the API Key, you only need to specify the vendor and model parameters. When you invoke the model service, the request is directly forwarded to the corresponding vendor's API.
Supported vendor list:
OpenAI - GPT Models
Anthropic - Claude Models
Google AI Studio - Gemini Models
DeepSeek - DeepSeek Models
MiniMax - MiniMax Text Models
Hunyuan - HY Models
Zhipu - GLM Models
Moonshot AI - Kimi Models