Skip to main content
POST
https://console.mixroute.io
/
v1
/
embeddings
curl --request POST \
  --url https://console.mixroute.io/v1/embeddings \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "text-embedding-3-small",
    "input": "你好，世界"
  }'

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, 0.015797347, ...]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5
  }
}

​
簡介

將文字轉換為向量嵌入，適用於語意搜尋、文字相似度計算、聚類分析等情境。

​
認證

Bearer Token，如 Bearer sk-xxxxxxxxxx

​
請求參數

​
model
string
required
模型名稱，如 text-embedding-3-small、text-embedding-3-large
​
input
string | array
required
要嵌入的文字，可以是字串或字串陣列
​
encoding_format
string
回傳格式：float 或 base64
​
dimensions
integer
輸出向量維度（僅部分模型支援）

​
cURL 範例

curl https://console.mixroute.io/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "你好，世界"
  }'

​
Python 範例

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxxxx",
    base_url="https://console.mixroute.io/v1"
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="你好，世界"
)

print(response.data[0].embedding)
print(f"向量維度：{len(response.data[0].embedding)}")

​
支援的模型

模型維度說明
text-embedding-3-small1536高性價比，適合大多數情境
text-embedding-3-large3072高精度，適合對精度要求高的情境
text-embedding-ada-0021536舊版模型

​
注意事項

  • 部分模型支援透過 dimensions 參數自訂輸出維度
  • 批次嵌入時，input 可傳入字串陣列
curl --request POST \
  --url https://console.mixroute.io/v1/embeddings \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "text-embedding-3-small",
    "input": "你好，世界"
  }'

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, 0.015797347, ...]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5
  }
}