New Model Support

We now support the Qwen3-Coder-480B-A35B model (model identifier: Qwen3-Coder), which is optimized for code generation and understanding, featuring a 256k context length and 64k maximum output length. It supports tools like Claude Code, Cline, Roo Code and more.

Quick Start

iFlow API provides 100% OpenAI-compatible interface services, allowing you to seamlessly switch to our AI services for higher performance and more cost-effective solutions.

Step 1: Get Your API Key

1. Visit iFlow and complete registration and login
2. Generate your exclusive API KEY by clicking Personal Information menu on the user settings page
3. Safely store the API KEY for subsequent API calls

💡 Tip: The API KEY has full account permissions. Do not disclose it to others.

Step 2: Understand Supported Models

We currently support the following AI models:

Model Name	Model Identifier	Context Length	Max Output Length
TBSTARS-2.0-200B-A13B	TBStars2-200B-A13B	32k	32k
DeepSeek-R1-671B	DeepSeek-R1	128k	32k
DeepSeek-V3-671B	DeepSeek-V3	128k	32k
Qwen3-32B	Qwen3-32B	128k	32k
Qwen3-235B-A22B	Qwen3-235B	128k	32k
Qwen3-Coder-480B-A35B	Qwen3-Coder	256k	64k
Kimi K2	KIMI-K2	128k	64k
Qwen3-235B-A22B-Thinking	Qwen3-235B-A22B-Thinking-2507	256k	64k
Qwen3-235B-A22B-Instruct	Qwen3-235B-A22B-Instruct	256k	64k

Step 3: Configure API Parameters

Use the following configuration information to call the iFlow API:

Parameter Name	Parameter Value	Description
Base URL	https://apis.iflow.cn/v1/chat/completions	Chat completion endpoint
API Key	your key	Obtain from Console, click Personal Information menu on the user settings page

Step 4: Start Calling the API

Basic Examples

Here are examples of calling the iFlow API using different programming languages:

Bash/cURL

curl https://apis.iflow.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "TBStars2-200B-A13B",
    "messages": [
      {"role": "system", "content": "You are a professional AI assistant."},
      {"role": "user", "content": "Please introduce the history of artificial intelligence development"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Python

import requests

# Configure API
url = "https://apis.iflow.cn/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

# Request data
data = {
    "model": "TBStars2-200B-A13B", 
    "messages": [
        {"role": "user", "content": "Explain the basic principles of quantum computing"}
    ],
    "temperature": 0.7,
    "max_tokens": 1000
}

# Make request
response = requests.post(url, json=data, headers=headers)
result = response.json()

# Print result
print(result["choices"][0]["message"]["content"])

JavaScript

const response = await fetch('https://apis.iflow.cn/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'TBStars2-200B-A13B',
    messages: [
      {role: 'user', content: 'Write a Python implementation of the quicksort algorithm'}
    ],
    temperature: 0.7,
    max_tokens: 1000
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Next Steps

• 📖 Detailed Documentation: View the complete API Reference Manual
• 🔧 Advanced Configuration: Learn more about parameter configuration options
• 💬 Technical Support: Visit Official Website for help

🚀 Start Building: Now that you've mastered the basics, you can start integrating the iFlow API into your projects!