GLM 4.7 Flash API - Speed Meets Affordability

import requests

API_URL = "https://open.bigmodel.cn/api/paas/v4/chat/completions"
API_KEY = "your-api-key"

def chat_with_flash(user_message):
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }

    data = {
        "model": "glm-4-flash",  # The key difference!
        "messages": [
            {"role": "user", "content": user_message}
        ],
        "temperature": 0.7,
        "max_tokens": 1000
    }

    response = requests.post(API_URL, headers=headers, json=data)
    return response.json()['choices'][0]['message']['content']

# Example usage
answer = chat_with_flash("What is machine learning?")
print(answer)
# Response time: ~0.8 seconds 🚀

const axios = require('axios');

const API_URL = "https://open.bigmodel.cn/api/paas/v4/chat/completions";
const API_KEY = process.env.GLM_API_KEY;

async function chatWithFlash(userMessage) {
  const response = await axios.post(API_URL, {
    model: "glm-4-flash",
    messages: [
      { role: "user", content: userMessage }
    ],
    temperature: 0.7,
    max_tokens: 1000
  }, {
    headers: {
      "Authorization": `Bearer ${API_KEY}`,
      "Content-Type": "application/json"
    }
  });

  return response.data.choices[0].message.content;
}

// Example usage
chatWithFlash("Tell me a fun fact about AI")
  .then(answer => console.log(answer))
  .catch(err => console.error(err));

import requests

def chat_with_flash_streaming(user_message):
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }

    data = {
        "model": "glm-4-flash",
        "messages": [{"role": "user", "content": user_message}],
        "stream": True  # Enable streaming for real-time responses
    }

    response = requests.post(API_URL, headers=headers, json=data, stream=True)

    # Print tokens as they arrive
    for line in response.iter_lines():
        if line:
            chunk = line.decode('utf-8')
            if chunk.startswith('data: '):
                print(chunk[6:], end='', flush=True)

# Even faster perceived response time with streaming!
chat_with_flash_streaming("Write a short poem about spring")