qwq-72b-preview
关于 qwq-72b-preview
QwQ-Preview is an experimental research model developed by the Qwen team in 2024, focused on enhancing AI reasoning capabilities, particularly in math and coding.
各路由分组价格
创建 Key 时可在控制台选择分组，状态实时来自路由。 查看各分组实时状态 →
| 分组 | 分组状态 | 模型状态 | 倍率 | 输入 | 输出 | 缓存读取 | 缓存写入 |
|---|---|---|---|---|---|---|---|
Self-Deployed-1 | … | ×0.507 | $38.025 | $38.025 | — | — | |
Self-Deployed-2 | … | ×0.845 | $63.375 | $63.375 | — | — |
USD / 百万 Token
支持的接口
openai
一个请求调用 qwq-72b-preview
兼容 OpenAI SDK 及任何 OpenAI 格式的客户端，把 Key 换成你自己的即可。
curl https://api.nixapi.com/v1/chat/completions \
-H "Authorization: Bearer $NIXAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwq-72b-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.nixapi.com/v1", api_key="sk-…")
resp = client.chat.completions.create(
model="qwq-72b-preview",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://api.nixapi.com/v1', apiKey: process.env.NIXAPI_KEY });
const resp = await client.chat.completions.create({
model: "qwq-72b-preview",
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(resp.choices[0].message.content);关于 qwq-72b-preview 的常见问题
qwq-72b-preview 在 NixAPI 上多少钱？
在 Self-Deployed-1 分组下，输入低至每百万 Token $38.025，输出低至每百万 Token $38.025，比官方价低约 49%。按量付费，以美元计价，没有月最低消费。
如何调用 qwq-72b-preview？
把任意兼容 OpenAI 格式的客户端指向 https://api.nixapi.com/v1，使用你的 NixAPI Key，并把 model 设为 "qwq-72b-preview" 即可。
哪些路由分组提供 qwq-72b-preview？
qwq-72b-preview 可在 2 个路由分组中使用：Self-Deployed-1、Self-Deployed-2。其中 Self-Deployed-1 分组价格最低。