Getting Started

Get integrated in three steps.

Endpoints

• API Base URL: $URL (your API endpoint domain — differs between China and Global environments; use the address assigned to your environment)
• Console: $CONSOLE_URL (for creating tokens and viewing usage)

In all examples below, $URL refers to your API base URL.

1. Get an API Key

1. Log in to the Console ($CONSOLE_URL)
2. Go to "Token Management" and click "Create Token"
3. Copy the generated Key (format sk-xxxx) and keep it safe

Note

An API Key is equivalent to your account credential. Do not write it into frontend code or public repositories. If leaked, delete and recreate it in the console immediately.

2. Make Your First Request

Here is an example using the chat completions endpoint (OpenAI-compatible format):

curl

curl $URL/v1/chat/completions \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="$URL/v1",
)

resp = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

TypeScript

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.YOUR_API_KEY,
  baseURL: '$URL/v1',
})

const resp = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello' }],
})
console.log(resp.choices[0].message.content)

3. Check Usage

Every call's model, token count and cost can be viewed in real time on the "Logs" page of the Console ($CONSOLE_URL).

Next Steps

• Text Generation API: GPT, Claude, DeepSeek, Gemini, GLM and more
• Image Generation API: GPT-Image, Gemini Image
• Video Generation API: Seedance 2.0, Seedance V3, Kling and more, plus two asset libraries (/v1/assets, /v3/assets)
• Error Codes: Troubleshoot calls