Quick Start

Step 1: Get Your API Key

Sign up and log in at 1688token.ai. Go to the Tokens page and create an API Key.

Include it in every request via the HTTP header:

Authorization: Bearer <your-api-key>

Step 2: Set the Base URL

1688token.ai is fully compatible with the OpenAI API format. All endpoints use the following base URL:

https://1688token.ai/v1

Just replace base_url in your existing code and you're done.

Step 3: Install the SDK

Python

pip install openai

Node.js

npm install openai

Step 4: Send Your First Request

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://1688token.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a professional AI assistant."},
        {"role": "user", "content": "Hello! Introduce yourself."}
    ]
)

print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://1688token.ai/v1"
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a professional AI assistant." },
    { role: "user", content: "Hello! Introduce yourself." }
  ]
});

console.log(response.choices[0].message.content);

cURL

curl https://1688token.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a professional AI assistant."},
      {"role": "user", "content": "Hello! Introduce yourself."}
    ]
  }'

Step 5: Common Endpoints

Endpoint	Method	Description
/v1/chat/completions	POST	Chat completion (supports streaming)
/v1/models	GET	List available models

Error Handling

When a request fails, the response body looks like:

{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Common HTTP status codes:

Status	Meaning	Action
401	Invalid or missing API Key	Check your Authorization header
403	Insufficient permissions or balance	Check account balance and Key permissions
429	Rate limit exceeded	Reduce request frequency or contact support
500	Internal server error	Retry after a moment

Rate Limits

Limit	Description
Request rate	Varies by account tier; returns 429 when exceeded
Max tokens	Depends on the selected model's context window
Response timeout	Set client timeout to 60s; relax for streaming requests