Qwen3 Embedding 8B API 接口、参数 & 代码示例

Qwen3 嵌入模型系列是 Qwen 系列中最新的专有模型，专为文本嵌入与排序任务设计。基于 Qwen3 系列的 dense 基础模型，该系列提供了多种规模（0.6B、4B、8B）的文本嵌入与重排序模型，继承了其基础模型在多语言能力、长文本理解与推理能力方面的优异表现。Qwen3 嵌入系列在多项文本嵌入与排序任务上实现了显著进展，包括文本检索、代码检索、文本分类、文本聚类与双语文本挖掘。

卓越的通用性：该嵌入模型在广泛的下游应用评估中达到了最先进的性能。8B 规模的嵌入模型在 MTEB 多语种排行榜中位列 第一（截至 2025 年 6 月 5 日，得分 70.58），而重排序模型在多种文本检索场景中表现优异。

全面的灵活性：Qwen3 嵌入系列在嵌入与重排序模型上提供了从 0.6B 到 8B 的全套规模，以满足侧重效率或效果的不同用例。开发者可以无缝组合这两类模块。此外，嵌入模型允许在所有维度上灵活定义向量，嵌入与重排序模型均支持用户自定义指令，以提升在特定任务、语言或场景下的表现。

多语言能力：借助 Qwen3 模型的多语言能力，Qwen3 嵌入系列支持 100 多种语言。这也包括多种编程语言，并为多语言、跨语言与代码检索提供了强大的能力。

Qwen3-Embedding-8B 主要特性：

• 模型类型：文本嵌入
• 支持语言：100+ 种语言
• 参数量：8B
• 上下文长度：32k
• 嵌入向量维度：最高 4096，支持用户自定义输出维度（32 至 4096）

此 API 接口兼容 OpenAI 的接口规范，也就是可以直接使用 OpenAI 的 SDK 来调用各个模型。仅需替换以下两项配置即可：

1. base_url 替换为 https://wcode.net/api/gpt/v1
2. api_key 替换为从 https://wcode.net/get-apikey 获取到的 API Key

具体可参考下方的各编程语言代码示例中的 openai sdk 调用示例。

# TODO: 以下代码中的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey

curl --request POST 'https://wcode.net/api/gpt/v1/embeddings' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer API_KEY' \
--data '{
    "model": "qwen/qwen3-embedding-8b",
    "input": ["苹果", "西瓜", "橙子"]
}'

import Foundation

let headers = [
  "Authorization": "Bearer API_KEY",     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
  "content-type": "application/json"
]
let parameters = [
  "model": "qwen/qwen3-embedding-8b",
  "input": ["苹果", "西瓜", "橙子"]
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://wcode.net/api/gpt/v1/embeddings")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 60.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()

var headers = {
  'Content-Type': 'application/json',
  'Authorization': 'Bearer API_KEY'     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
};
var request = http.Request('POST', Uri.parse('https://wcode.net/api/gpt/v1/embeddings'));
request.body = json.encode({
  "model": "qwen/qwen3-embedding-8b",
  "input": ["苹果", "西瓜", "橙子"]
});
request.headers.addAll(headers);

http.StreamedResponse response = await request.send();

if (response.statusCode == 200) {
  print(await response.stream.bytesToString());
}
else {
  print(response.reasonPhrase);
}

require 'uri'
require 'net/http'

url = URI("https://wcode.net/api/gpt/v1/embeddings")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer API_KEY'     # TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
request["content-type"] = 'application/json'
request.body = "{\"model\":\"qwen/qwen3-embedding-8b\",\"input\":[\"苹果\",\"西瓜\",\"橙子\"]}"

response = http.request(request)
puts response.read_body

use serde_json::json;
use reqwest;

#[tokio::main]
pub async fn main() {
  let url = "https://wcode.net/api/gpt/v1/embeddings";

  let payload = json!({
    "model": "qwen/qwen3-embedding-8b",
    "input": ["苹果", "西瓜", "橙子"]
  });

  let mut headers = reqwest::header::HeaderMap::new();
  headers.insert("Authorization", "Bearer API_KEY".parse().unwrap());     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
  headers.insert("content-type", "application/json".parse().unwrap());

  let client = reqwest::Client::new();
  let response = client.post(url)
    .headers(headers)
    .json(&payload)
    .send()
    .await;

  let results = response.unwrap()
    .json::<serde_json::Value>()
    .await
    .unwrap();

  dbg!(results);
}

CURL *hnd = curl_easy_init();

curl_easy_setopt(hnd, CURLOPT_CUSTOMREQUEST, "POST");
curl_easy_setopt(hnd, CURLOPT_URL, "https://wcode.net/api/gpt/v1/embeddings");

struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "Authorization: Bearer API_KEY");    // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
headers = curl_slist_append(headers, "content-type: application/json");
curl_easy_setopt(hnd, CURLOPT_HTTPHEADER, headers);

curl_easy_setopt(hnd, CURLOPT_POSTFIELDS, "{\"model\":\"qwen/qwen3-embedding-8b\",\"input\":[\"苹果\",\"西瓜\",\"橙子\"]}");

CURLcode ret = curl_easy_perform(hnd);

package main

import (
  "fmt"
  "strings"
  "net/http"
  "io"
)

func main() {
  url := "https://wcode.net/api/gpt/v1/embeddings"

  payload := strings.NewReader("{\"model\":\"qwen/qwen3-embedding-8b\",\"input\":[\"苹果\",\"西瓜\",\"橙子\"]}")

  req, _ := http.NewRequest("POST", url, payload)

  req.Header.Add("Authorization", "Bearer API_KEY")     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
  req.Header.Add("content-type", "application/json")

  res, _ := http.DefaultClient.Do(req)

  defer res.Body.Close()
  body, _ := io.ReadAll(res.Body)

  fmt.Println(res)
  fmt.Println(string(body))
}

using System.Net.Http.Headers;


var client = new HttpClient();

var request = new HttpRequestMessage(HttpMethod.Post, "https://wcode.net/api/gpt/v1/embeddings");

request.Headers.Add("Authorization", "Bearer API_KEY");     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey

request.Content = new StringContent("{\"model\":\"qwen/qwen3-embedding-8b\",\"input\":[\"苹果\",\"西瓜\",\"橙子\"]}", null, "application/json");

var response = await client.SendAsync(request);

response.EnsureSuccessStatusCode();

Console.WriteLine(await response.Content.ReadAsStringAsync());

var client = new RestClient("https://wcode.net/api/gpt/v1/embeddings");

var request = new RestRequest("", Method.Post);

request.AddHeader("Authorization", "Bearer API_KEY");     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey

request.AddHeader("content-type", "application/json");

request.AddParameter("application/json", "{\"model\":\"qwen/qwen3-embedding-8b\",\"input\":[\"苹果\",\"西瓜\",\"橙子\"]}", ParameterType.RequestBody);

var response = client.Execute(request);

const axios = require('axios');

let data = JSON.stringify({
  "model": "qwen/qwen3-embedding-8b",
  "input": ["苹果", "西瓜", "橙子"]
});

let config = {
  method: 'post',
  maxBodyLength: Infinity,
  url: 'https://wcode.net/api/gpt/v1/embeddings',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer API_KEY'     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
  },
  data : data
};

axios.request(config).then((response) => {
  console.log(JSON.stringify(response.data));
}).catch((error) => {
  console.log(error);
});

OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("application/json");

RequestBody body = RequestBody.create(mediaType, "{\"model\":\"qwen/qwen3-embedding-8b\",\"input\":[\"苹果\",\"西瓜\",\"橙子\"]}");

Request request = new Request.Builder()
  .url("https://wcode.net/api/gpt/v1/embeddings")
  .post(body)
  .addHeader("Authorization", "Bearer API_KEY")             // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
  .addHeader("content-type", "application/json")
  .build();

Response response = client.newCall(request).execute();

$client = new \GuzzleHttp\Client();

$headers = [
  'Content-Type' => 'application/json',
  'Authorization' => 'Bearer API_KEY',     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
];

$body = '{
  "model": "qwen/qwen3-embedding-8b",
  "input": ["苹果", "西瓜", "橙子"]
}';

$request = new \GuzzleHttp\Psr7\Request('POST', 'https://wcode.net/api/gpt/v1/embeddings', $headers, $body);

$response = $client->sendAsync($request)->wait();

echo $response->getBody();

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://wcode.net/api/gpt/v1/embeddings",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 5,
  CURLOPT_TIMEOUT => 300,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'qwen/qwen3-embedding-8b',
    'input' => ['苹果', '西瓜', '橙子']
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer API_KEY",     // TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
    "content-type: application/json",
  ],
]);

$response = curl_exec($curl);
$error = curl_error($curl);

curl_close($curl);

if ($error) {
  echo "cURL Error #:" . $error;
} else {
  echo $response;
}

import requests
import json

url = "https://wcode.net/api/gpt/v1/embeddings"

payload = {
  "model": "qwen/qwen3-embedding-8b",
  "input": ["苹果", "西瓜", "橙子"]
}

headers = {
  "Authorization": "Bearer API_KEY",     # TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
  "content-type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(json.dumps(response.json(), indent=4, ensure_ascii=False))

from openai import OpenAI

client = OpenAI(
  base_url="https://wcode.net/api/gpt/v1",
  api_key="API_KEY"                             # TODO: 这里的 API_KEY 需要替换，获取 API Key 入口：https://wcode.net/get-apikey
)

completion = client.chat.completions.create(
  model="qwen/qwen3-embedding-8b",
  input=["苹果", "西瓜", "橙子"]
)

print(completion.choices[0].message.content)

{
    "id": "chatcmpl-t1770400451s602re3370c9df37bacad4adc5e75",
    "object": "list",
    "data": [
        {
            "object": "embedding",
            "embedding": [
                -0.0022789943031966686,
                0.005342807620763779,
                0.0008489630999974906,
                0.01128932274878025,
                0.017748989164829254,
                ...
            ],
            "index": 0
        },
        {
            "object": "embedding",
            "embedding": [
                0.0004407314117997885,
                0.004681382328271866,
                0.0063998643308877945,
                -0.013155276887118816,
                0.017184821888804436,
                ...
            ],
            "index": 1
        },
        {
            "object": "embedding",
            "embedding": [
                0.014811988919973373,
                -0.009736964479088783,
                0.01251052413135767,
                -0.011861393228173256,
                0.016051238402724266,
                ...
            ],
            "index": 2
        }
    ],
    "model": "Qwen/Qwen3-Embedding-8B",
    "usage": {
        "prompt_tokens": 7,
        "total_tokens": 7
    }
}