const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    Accept: 'text/event-stream',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'qwen-3.8-max-text-to-text',
    messages: [
      {
        role: 'user',
        content: 'Explain the concept of attention mechanisms in neural networks.'
      }
    ],
    stream: true,
    max_tokens: 2048,
    top_p: 0.9,
    top_k: 50
  })
});

const reader = response.body.getReader();
const decoder = new TextDecoder();
let buffer = '';
let assistantText = '';

while (true) {
  const { done, value } = await reader.read();
  if (done) break;

  buffer += decoder.decode(value, { stream: true });
  const frames = buffer.split('\n\n');
  buffer = frames.pop() || '';

  for (const frame of frames) {
    const lines = frame.split('\n').filter(Boolean);
    let eventName = 'message';
    const dataLines = [];

    for (const line of lines) {
      if (line.startsWith('event:')) {
        eventName = line.slice(6).trim();
      } else if (line.startsWith('data:')) {
        dataLines.push(line.replace(/^data:\s*/, ''));
      }
    }

    const raw = dataLines.join('\n').trim();
    if (raw === '[DONE]') {
      console.log('\nFinal text:', assistantText);
      continue;
    }

    let payload;
    try {
      payload = JSON.parse(raw);
    } catch {
      continue;
    }

    if (eventName === 'error' || payload.error) {
      const msg = payload.error?.message ?? payload.message ?? 'Chat request failed';
      throw new Error(msg);
    }

    const delta = payload.choices?.[0]?.delta;
    if (delta?.content) {
      assistantText += delta.content;
      console.log(assistantText);
    }
  }
}

import json
import requests

response = requests.post(
    'https://api.flaq.ai/api/v1/chat/completions',
    headers={
        'Authorization': 'Bearer YOUR_API_KEY',
        'Accept': 'text/event-stream',
        'Content-Type': 'application/json',
    },
    json={
        'model': 'qwen-3.8-max-text-to-text',
        'messages': [
            {
                'role': 'user',
                'content': 'Explain the concept of attention mechanisms in neural networks.',
            }
        ],
        'stream': True,
        'max_tokens': 2048,
        'top_p': 0.9,
        'top_k': 50,
    },
    stream=True,
)

response.raise_for_status()

event_name = 'message'
assistant_text = ''

for raw_line in response.iter_lines(decode_unicode=True):
    if not raw_line:
        event_name = 'message'
        continue

    if raw_line.startswith('event:'):
        event_name = raw_line.replace('event:', '', 1).strip()
        continue

    if raw_line.startswith('data:'):
        raw_data = raw_line.replace('data:', '', 1).strip()
        if raw_data == '[DONE]':
            print('\nFinal text:', assistant_text)
            continue

        payload = json.loads(raw_data)

        if event_name == 'error' or payload.get('error'):
            error = payload.get('error') or payload
            raise RuntimeError(error.get('message', 'Chat request failed'))

        choices = payload.get('choices') or []
        if choices:
            delta = choices[0].get('delta') or {}
            content = delta.get('content')
            if content:
                assistant_text += content
                print(content, end='', flush=True)

curl -N -X POST "https://api.flaq.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Accept: text/event-stream" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-3.8-max-text-to-text",
    "messages": [
      {
        "role": "user",
        "content": "Explain the concept of attention mechanisms in neural networks."
      }
    ],
    "stream": true,
    "max_tokens": 2048,
    "top_p": 0.9,
    "top_k": 50
  }'