> ## Documentation Index
> Fetch the complete documentation index at: https://docs.senseaudio.cn/llms.txt
> Use this file to discover all available pages before exploring further.
# 快速接入
> 订阅 Token Plan、获取 API Key 并完成首个模型调用
本页引导您在 5 分钟内完成 Token Plan 的订阅、密钥获取，并通过 OpenAI 兼容接口完成首个调用。SenseAudio 自研提供 **S2 系列（旗舰 / Flash / Lite）**，默认示例以 **SenseAudio-S2**（`senseaudio-s2`）为例。
## 开始使用
进入 [SenseAudio 官网](https://senseaudio.cn/)，在顶部导航点击 **Token Plan**。
页面滚动到套餐区域，按需求选择 **Pro（¥199）/ Max（¥699）/ Ultra（¥1,899）** 任一档位，点击「开始」按钮完成支付。
支付完成后，在官网顶部导航点击 **API 平台**，在下拉菜单的 **开发者** 区域选择 **API 密钥**，进入API密钥页面
进入 API 密钥页面后，点击右上角的 **+ 创建新密钥**，复制生成的 Key 并妥善保存。该 Key 可直接用于 Token Plan 的模型调用。
**重要提示**
* 套餐额度用尽或达到限制后，可开启 **Extra Usage**，超出部分自动按量计费、从账户积分余额扣费。
* API Key 仅展示一次，强烈建议立即设置为环境变量：
```bash theme={null}
export SENSEAUDIO_API_KEY="sk-xxxxxx"
```
* 请勿提交到公共仓库或泄露给他人。
SenseAudio Token Plan 提供 **OpenAI 兼容**接口，示例以 **SenseAudio-S2**（`senseaudio-s2`）为例，替换 `model` 字段即可切换到 **S2-Flash**（`senseaudio-s2-flash`）、**S2-Lite**（`senseaudio-s2-lite`）、**VL-1.0**（`senseaudio-vl-1.0-260319`）、**VL-Lite-1.0**（`senseaudio-vl-lite-1.0-260319`）或第三方模型（如 `glm-5.1` / `minimax-m2.7` / `qwen3.6-35b-a3b` / `deepseek-v4-pro` 等）。
Base URL：`https://api.senseaudio.cn/v1`
```bash cURL theme={null}
curl https://api.senseaudio.cn/v1/chat/completions \
-H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "senseaudio-s2",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "用一句话介绍你自己。"}
]
}'
```
```python Python theme={null}
# pip install openai
from openai import OpenAI
client = OpenAI(
api_key="",
base_url="https://api.senseaudio.cn/v1",
)
resp = client.chat.completions.create(
model="senseaudio-s2",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "用一句话介绍你自己。"},
],
)
print(resp.choices[0].message.content)
```
```javascript Node.js theme={null}
// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.SENSEAUDIO_API_KEY,
baseURL: "https://api.senseaudio.cn/v1",
});
const resp = await client.chat.completions.create({
model: "senseaudio-s2",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "用一句话介绍你自己。" },
],
});
console.log(resp.choices[0].message.content);
```
```go Go theme={null}
// go get github.com/sashabaranov/go-openai
package main
import (
"context"
"fmt"
"os"
"github.com/sashabaranov/go-openai"
)
func main() {
config := openai.DefaultConfig(os.Getenv("SENSEAUDIO_API_KEY"))
config.BaseURL = "https://api.senseaudio.cn/v1"
client := openai.NewClientWithConfig(config)
resp, err := client.CreateChatCompletion(
context.Background(),
openai.ChatCompletionRequest{
Model: "senseaudio-s2",
Messages: []openai.ChatCompletionMessage{
{Role: openai.ChatMessageRoleSystem, Content: "You are a helpful assistant."},
{Role: openai.ChatMessageRoleUser, Content: "用一句话介绍你自己。"},
},
},
)
if err != nil {
fmt.Println("请求失败:", err)
return
}
fmt.Println(resp.Choices[0].Message.Content)
}
```
```java Java theme={null}
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class QuickStart {
public static void main(String[] args) throws Exception {
String apiKey = System.getenv("SENSEAUDIO_API_KEY");
String body = """
{
"model": "senseaudio-s2",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "用一句话介绍你自己。"}
]
}
""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://api.senseaudio.cn/v1/chat/completions"))
.header("Authorization", "Bearer " + apiKey)
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(body))
.build();
HttpResponse response = HttpClient.newHttpClient()
.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
```
Endpoint：`https://api.senseaudio.cn/v1/responses`
```bash cURL theme={null}
curl https://api.senseaudio.cn/v1/responses \
-H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "senseaudio-s2",
"input": "用一句话介绍你自己。"
}'
```
```python Python theme={null}
# pip install openai
from openai import OpenAI
client = OpenAI(
api_key="",
base_url="https://api.senseaudio.cn/v1",
)
resp = client.responses.create(
model="senseaudio-s2",
input="用一句话介绍你自己。",
)
print(resp.output_text)
```
```javascript Node.js theme={null}
// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.SENSEAUDIO_API_KEY,
baseURL: "https://api.senseaudio.cn/v1",
});
const resp = await client.responses.create({
model: "senseaudio-s2",
input: "用一句话介绍你自己。",
});
console.log(resp.output_text);
```
挑选您常用的 AI 编程工具完成配置，即可在实际项目里体验 **SenseAudio Token Plan**。
## 最佳实践
SenseAudio S2 系列的高效 Prompt 模式、长任务推理与状态跟踪。
Step-by-step 任务模板，把 Agent 用熟。