qwen/qwen3-coder-next
发布时间: 2026-02-04
262,144 context · $0.15/M input tokens · $0.80/M output tokens
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
定价
按量付费
无需预付费用，仅按实际使用量付费
试用模型
API 使用
使用以下代码示例接入我们的 API：
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-coder-next',
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-coder-next',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}模型介绍
Qwen qwen3-coder-next
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment.
The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.
Why It Looks Great
- Large Language Model architecture for efficient processing
- 262144 context window for long document handling
- Competitive pricing at $0.1/$0.3 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 | $0.1 |
| Output | $0.3 |
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-coder-next
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-coder-next",
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-coder-next",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: qwen/qwen3-coder-next
- Provider: Qwen
信息
支持功能
API 访问指南
Qwen3 Coder Next API
qwen/qwen3-coder-next
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
输入
$0.15 /M
输出
$0.8 /M
上下文
262K
最大输出
66K
工具调用
支持
在 WaveSpeedAI 试用 Qwen3 Coder Next
通过我们的统一 API 接入 Qwen3 Coder Next — 兼容 OpenAI、无冷启动、透明计费。
关于 Qwen3 Coder Next 的常见问题
Qwen3 Coder Next API 多少钱?+
WaveSpeedAI 定价:输入每百万 token $0.15,输出每百万 token $0.80。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。
Qwen3 Coder Next 的上下文窗口是多大?+
Qwen3 Coder Next 单次请求最多支持 262K 上下文 token,输出最多 66K token。
Qwen3 Coder Next 是否兼容 OpenAI?+
WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容 Chat Completions 接口提供 Qwen3 Coder Next。大多数 OpenAI SDK 客户端只需更换 base URL 和 API Key；可选字段取决于具体模型。
如何开始使用 Qwen3 Coder Next?+
登录 WaveSpeedAI，在 Access Keys 中创建 API Key，然后使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。模型可用性、能力和价格请以当前模型目录为准。