qwen/qwen3.5-397b-a17b
リリース日: 2026-02-16
262,144 context · $0.60/M input tokens · $3.60/M output tokens
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.
料金
従量課金
初期費用なし、使った分だけお支払い
モデルを試す
API 利用
以下のコード例を使用して API と連携してください:
import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'qwen/qwen3.5-397b-a17b',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'qwen/qwen3.5-397b-a17b',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}モデル紹介
Qwen qwen3.5-397b-a17b
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.
Why It Looks Great
- Large Language Model architecture for efficient processing
- 262144 context window for long document handling
- Competitive pricing at $0.4/$2.3 per million tokens
Key Features
- Context Window: 262144 tokens
- Max Output: 65536 tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Qwen |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 262144 tokens |
| Max Output | 65536 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.4 |
| Output | $2.3 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: qwen/qwen3.5-397b-a17b
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="qwen/qwen3.5-397b-a17b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "qwen/qwen3.5-397b-a17b",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: qwen/qwen3.5-397b-a17b
- Provider: Qwen
情報
対応機能
API アクセスガイド
Qwen3.5 397b A17b API
qwen/qwen3.5-397b-a17b
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.
入力
$0.6 /M
出力
$3.6 /M
コンテキスト
262K
最大出力
66K
Vision
対応
ツール利用
対応
WaveSpeedAIでQwen3.5 397b A17bを試す
統合APIを通じてQwen3.5 397b A17bにアクセス — OpenAI互換、コールドスタートなし、透明な料金。
Qwen3.5 397b A17bに関するよくある質問
Qwen3.5 397b A17b API の料金はいくらですか?+
WaveSpeedAI の料金: 入力 100 万トークンあたり $0.60、出力 100 万トークンあたり $3.60。プロンプトキャッシュとバッチ処理は別途料金で、長く反復的なワークロードでは実効コストを下げられます。
Qwen3.5 397b A17b のコンテキストウィンドウはどのくらいですか?+
Qwen3.5 397b A17b はリクエストあたり最大 262K のコンテキストトークンと最大 66K の出力トークンをサポートします。
Qwen3.5 397b A17b は OpenAI 互換ですか?+
WaveSpeedAI は https://llm.wavespeed.ai/v1 の OpenAI 互換 Chat Completions インターフェースで Qwen3.5 397b A17b を提供します。多くの OpenAI SDK クライアントはベース URL と API キーの変更で利用できますが、オプション項目はモデルごとに異なります。
Qwen3.5 397b A17b を使い始めるには?+
WaveSpeedAI にサインインし、Access Keys で API キーを作成して、上に表示されたモデル ID を指定して https://llm.wavespeed.ai/v1/chat/completions にリクエストを送信してください。提供状況、機能、料金は最新のモデルカタログで確認してください。