Alibaba/qwen-flash-character

qwen-flash-character

Free to try Qwen Flash Character API for fast persona-driven text roleplay, profile, memory, and scalable Alibaba LLM workflows.

Text Chat

Documentation

API Examples

JavaScriptPythoncURL

Submit Example

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-flash-character',
    messages: [
      {
        role: 'system',
        content: 'You are a calm library assistant who speaks briefly and vividly.'
      },
      {
        role: 'user',
        content: 'Introduce yourself in three sentences.'
      }
    ],
    stream: true,
    max_tokens: 800,
    temperature: 0.7,
    seed: 12345
  })
});

if (!response.ok) {
  const errorBody = await response.json().catch(() => null);
  throw new Error(errorBody?.error?.message ?? errorBody?.message ?? `HTTP ${response.status}`);
}

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(/\r?\n\r?\n/);
  buffer = frames.pop() || '';

  for (const frame of frames) {
    const lines = frame.split(/\r?\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);
    }
  }
}

Submit Example

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-flash-character',
        'messages': [
            {
                'role': 'system',
                'content': 'You are a calm library assistant who speaks briefly and vividly.',
            },
            {
                'role': 'user',
                'content': 'Introduce yourself in three sentences.',
            },
        ],
        'stream': True,
        'max_tokens': 800,
        'temperature': 0.7,
        'seed': 12345,
    },
    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)

Submit Example

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-flash-character",
    "messages": [
      {
        "role": "system",
        "content": "You are a calm library assistant who speaks briefly and vividly."
      },
      {
        "role": "user",
        "content": "Introduce yourself in three sentences."
      }
    ],
    "stream": true,
    "max_tokens": 800,
    "temperature": 0.7,
    "seed": 12345
  }'

Start a new chat

Send a message to begin.

Qwen Flash Character Pricing

Parameters	Price	Original Price	Discount

Token: input	$0.0500 per 1M input tokens	-	Standard
Token: output	$0.4000 per 1M output tokens	-	Standard

README

Fast & Affordable Qwen Flash Character API (Alibaba Character Roleplay LLM)

Qwen Flash Character API on Flaq AI provides fast, cost-effective Alibaba character roleplay LLM access for chat products, companion apps, storytelling systems, and persona-driven workflows. This affordable Qwen API integration helps developers generate character-consistent text responses quickly while supporting prompt-guided tone, profile setup, and conversation context. It is designed for rapid iteration, high-volume dialogue testing, and scalable roleplay features.

Key Features of Qwen Flash Character API

Fast Character Dialogue: Generate persona-aligned text responses quickly for prototypes, roleplay apps, assistants, and high-volume conversation workflows.
Cost-Effective API Access: Use Qwen Flash Character for affordable character chat without maintaining custom model infrastructure.
Prompt-Guided Persona Control: Define character background, tone, speaking style, and response behavior through system messages, with profile used for long-term memory mode.
Consistent Conversation Direction: Keep dialogue aligned with recognizable character traits and session context across turns.
Long-Term Memory Support: Reuse memory across related conversations with enable_long_term_memory, profile, and a user-defined x-session value.
Group Chat Simulation: Simulate multi-speaker scenes by manually writing speaker names in message content and using an assistant prefix with partial: true.
Flexible Roleplay Coverage: Build companions, story characters, training personas, support bots, and interactive fiction experiences.
Developer-Friendly Integration: Add rapid character LLM workflows to products through Flaq AI's managed Alibaba API route.

How to Use Qwen Flash Character API for Rapid Character Chat on Flaq AI

Input: Text chat messages, system persona instructions, optional long-term memory settings, and optional assistant partial continuation messages.
Output: Text responses for character dialogue, roleplay, storytelling, and persona-driven chat experiences.
Conversation Control: Supports prompt-based direction for identity, tone, memory behavior, response style, short-term context, and long-term session continuity.
Capabilities: Fast roleplay dialogue, character-consistent text generation, persona chat, group-chat simulation, partial assistant continuation, interactive storytelling, and scalable character workflows through Qwen Flash Character API integration.

For group-chat simulation, speaker names are not inferred from profile. Add names manually at the beginning of each message, then append a final assistant message such as Ling Lu: with partial: true so the model continues as that character.

Best Use Cases for Qwen Flash Character API Integration

Rapid Dialogue Iteration: Test character voices, profiles, and interaction styles quickly before selecting a final persona direction.
Companion & Roleplay Apps: Power user-facing products that need fast character chat, lightweight memory, and affordable text generation.
Story & Game Prototyping: Explore dialogue, NPC behavior, branching scenes, and character interactions for early-stage product development.
Training & Simulation: Create role-based conversation practice for language learning, coaching, support training, and scenario rehearsal.
High-Volume Chat Workflows: Support scalable roleplay and persona-chat systems where speed and affordability matter.

Note Please ensure prompts, character profiles, memory usage, and generated text comply with Alibaba and Flaq AI safety requirements. If an error occurs, revise the request, profile, or generation settings and try again.

Qwen Flash Character vs Competitors: Comparative Analysis

Qwen Flash Character vs. Qwen Plus Character
Qwen Plus Character is positioned for richer roleplay and more polished persona-driven responses. Qwen Flash Character prioritizes fast, affordable dialogue for iteration-heavy workflows.
Qwen Flash Character vs. GPT Character Chat GPT models support broad general-purpose conversation. Qwen Flash Character focuses on rapid Alibaba-powered character chat workflows with managed API access.
Qwen Flash Character vs. Claude Character Chat Claude is useful for careful long-form dialogue. Qwen Flash Character offers a faster, lower-cost route for scalable roleplay and companion chat products.
Qwen Flash Character vs. Kimi Text-to-Text Kimi is useful for general LLM reasoning and writing. Qwen Flash Character focuses on character persona behavior, roleplay response style, and high-volume dialogue.
Qwen Flash Character vs. General Qwen Chat General Qwen chat models cover broad text tasks. Qwen Flash Character is optimized for persona-led conversations where speed, affordability, and character consistency matter.