Gemini 文本向量（embedContent）

curl --request POST \
  --url https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "content": {
      "parts": [{"text": "这是一段测试文本"}]
    }
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"
headers = {
    "Authorization": "Bearer sk-xxxxxxxxxx",
    "Content-Type": "application/json"
}
payload = {
    "content": {
        "parts": [{"text": "这是一段测试文本"}]
    }
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

const response = await fetch('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    content: {
      parts: [{ text: '这是一段测试文本' }]
    }
  })
});
const data = await response.json();
console.log(data);

<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'content' => [
            'parts' => [['text' => '这是一段测试文本']]
        ]
    ]
]);
echo $response->getBody();

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "content": map[string]interface{}{
            "parts": []map[string]string{
                {"text": "这是一段测试文本"},
            },
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}

import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "content": {"parts": [{"text": "这是一段测试文本"}]}
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  content: { parts: [{ text: '这是一段测试文本' }] }
}.to_json

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

{
  "embedding": {
    "values": [0.0023064255, -0.009327292, 0.015797347]
  },
  "metadata": {
    "usage": {
      "prompt_tokens": 6,
      "total_tokens": 6
    }
  }
}

POST

models

{model}

:embedContent

curl --request POST \
  --url https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "content": {
      "parts": [{"text": "这是一段测试文本"}]
    }
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"
headers = {
    "Authorization": "Bearer sk-xxxxxxxxxx",
    "Content-Type": "application/json"
}
payload = {
    "content": {
        "parts": [{"text": "这是一段测试文本"}]
    }
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

const response = await fetch('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    content: {
      parts: [{ text: '这是一段测试文本' }]
    }
  })
});
const data = await response.json();
console.log(data);

<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'content' => [
            'parts' => [['text' => '这是一段测试文本']]
        ]
    ]
]);
echo $response->getBody();

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "content": map[string]interface{}{
            "parts": []map[string]string{
                {"text": "这是一段测试文本"},
            },
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}

import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "content": {"parts": [{"text": "这是一段测试文本"}]}
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  content: { parts: [{ text: '这是一段测试文本' }] }
}.to_json

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

{
  "embedding": {
    "values": [0.0023064255, -0.009327292, 0.015797347]
  },
  "metadata": {
    "usage": {
      "prompt_tokens": 6,
      "total_tokens": 6
    }
  }
}

简介

使用 Gemini 原生接口将文本转换为向量嵌入。模型由 URL 路径指定（如 gemini-embedding-001），适用于需要 Google 嵌入模型或与 Gemini API 对齐的场景。与文本向量化（Embedding）的 OpenAI 格式互为补充：本文档为 Gemini 原生路径；同一能力也可通过 POST /v1/embeddings 调用。

认证

Bearer Token，如 Bearer sk-xxxxxxxxxx

路径参数

string

required

嵌入模型名称，如 gemini-embedding-001。

请求参数

object

required

待嵌入内容。须包含 parts 数组，每项为 { "text": "文本内容" }。

integer

输出向量维度（仅部分模型支持，如 gemini-embedding-001、text-embedding-004）。

string

任务类型，如 RETRIEVAL_DOCUMENT、RETRIEVAL_QUERY（可选）。

代码示例

cURL
cURL（带维度）
Python

curl -X POST "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "content": {
      "parts": [
        { "text": "要嵌入的文本内容" }
      ]
    }
  }'

curl -X POST "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "content": {
      "parts": [
        { "text": "要嵌入的文本内容" }
      ]
    },
    "outputDimensionality": 768
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-xxxxxxxxxx"
}
payload = {
    "content": {
        "parts": [
            { "text": "要嵌入的文本内容" }
        ]
    }
}

response = requests.post(url, json=payload, headers=headers)
data = response.json()
embedding = data["embedding"]["values"]
print(f"向量维度：{len(embedding)}")

响应示例

{
  "embedding": {
    "values": [0.0023064255, -0.009327292, 0.015797347, ...]
  },
  "metadata": {
    "usage": {
      "prompt_tokens": 6,
      "total_tokens": 6
    }
  }
}

批量接口（batchEmbedContents）

批量嵌入请使用：POST /v1/models/{model}:batchEmbedContents，请求体为 requests 数组，每项结构同单条（含 content.parts），且不要在每项中带 model 字段。

curl -X POST "https://api.mixroute.ai/v1/models/gemini-embedding-001:batchEmbedContents" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "requests": [
      { "content": { "parts": [{ "text": "第一段文本" }] } },
      { "content": { "parts": [{ "text": "第二段文本" }] } }
    ]
  }'

支持的模型

模型	说明
gemini-embedding-001	通用嵌入模型，支持 `outputDimensionality`
text-embedding-004	高精度嵌入模型

注意事项

content.parts 必填，至少一个 text 非空
模型由 URL 路径指定，请求体不要包含 model 字段
用量信息在响应的 metadata.usage 中（prompt_tokens、total_tokens）

如果您的应用已使用 OpenAI SDK，建议使用 /v1/embeddings 兼容接口以减少代码改动。

curl --request POST \
  --url https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "content": {
      "parts": [{"text": "这是一段测试文本"}]
    }
  }'

import requests

url = "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"
headers = {
    "Authorization": "Bearer sk-xxxxxxxxxx",
    "Content-Type": "application/json"
}
payload = {
    "content": {
        "parts": [{"text": "这是一段测试文本"}]
    }
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())

const response = await fetch('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxxxxxxxx',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    content: {
      parts: [{ text: '这是一段测试文本' }]
    }
  })
});
const data = await response.json();
console.log(data);

<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'content' => [
            'parts' => [['text' => '这是一段测试文本']]
        ]
    ]
]);
echo $response->getBody();

package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "content": map[string]interface{}{
            "parts": []map[string]string{
                {"text": "这是一段测试文本"},
            },
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}

import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "content": {"parts": [{"text": "这是一段测试文本"}]}
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/models/gemini-embedding-001:embedContent')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  content: { parts: [{ text: '这是一段测试文本' }] }
}.to_json

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

{
  "embedding": {
    "values": [0.0023064255, -0.009327292, 0.015797347]
  },
  "metadata": {
    "usage": {
      "prompt_tokens": 6,
      "total_tokens": 6
    }
  }
}

文本向量化（Embedding）Gemini 原生（图像）

当下热门模型

智能路由

OpenAI 官方库使用

文本系列

文本向量系列

图像系列

视频系列

其他

Gemini 文本向量（embedContent）

简介

认证

路径参数

请求参数

代码示例

响应示例

批量接口（batchEmbedContents）

支持的模型

注意事项

​简介

​认证

​路径参数

​请求参数

​代码示例

​响应示例

​批量接口（batchEmbedContents）

​支持的模型

​注意事项

简介

认证

路径参数

请求参数

代码示例

响应示例

批量接口（batchEmbedContents）

支持的模型

注意事项