Embeddings

POST /v1/embeddings

Converts text into vectors for semantic search, RAG, clustering, and recommendations.

RequestREQUEST

POSThttps://test.kailin.com.cn/v1/embeddings

API KeyStored only in your browser, never uploaded

Body (JSON){ "model": "text-embedding-3-small", "input": "AI Station is a unified model gateway" }

ResponseRESPONSE

Fill in the request and hit Send — the response shows up here

Request

curl https://test.kailin.com.cn/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-token" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "AI Station is a unified model gateway"
  }'

Request Body

Parameter	Type	Required	Description
model	string	Yes	Embedding model, e.g. text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002
input	string / array	Yes	A string or an array of strings (batch) — per-request limits depend on the model
dimensions	integer	No	Output vector dimensions (text-embedding-3 series supports dimension reduction)
encoding_format	string	No	float (default) or base64
user	string	No	End-user identifier

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0154, "..."]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

Field	Description
data[].embedding	Vector array — default 1536 dimensions (text-embedding-3-small) / 3072 (-large)
data[].index	Index of the corresponding input string
usage.prompt_tokens	Billed token count

Batch Requests

{
  "model": "text-embedding-3-small",
  "input": ["first document", "second document", "third document"]
}

The returned data carries index matching the input order. A single batched call is faster and cheaper on request count than per-item calls.

Using the SDK

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-token",
    base_url="https://test.kailin.com.cn/v1",
)

resp = client.embeddings.create(
    model="text-embedding-3-small",
    input=["Document A", "Document B"],
)
vectors = [item.embedding for item in resp.data]

note

Gemini-native embedding endpoints (/v1beta/models/{model}:embedContent etc.) are also proxied — parameters follow the Gemini official format, see Google's documentation.