Embeddings
Convert text into high-dimensional vectors for semantic search, similarity, and RAG, compatible with the OpenAI Embeddings protocol.
Basics
MethodPOST
Endpointhttps://koprouter.kopglobal.com/v1/embeddings
AuthenticationAuthorization: Bearer sk-...
Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model |
string | Yes | Embedding model ID |
input |
string/array | Yes | Text to embed — a string or an array of strings |
encoding_format |
string | No | Output format, float (default) or base64 |
dimensions |
number | No | Target vector dimensions |
Example Request
curl https://koprouter.kopglobal.com/v1/embeddings \
-H "Authorization: Bearer sk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "MODEL_ID",
"input": ["Hello world", "你好，世界"]
}'
Example Response
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.0023, -0.0112, 0.0184]
},
{
"object": "embedding",
"index": 1,
"embedding": [0.0019, -0.0108, 0.0177]
}
],
"model": "MODEL_ID",
"usage": {
"prompt_tokens": 5,
"total_tokens": 5
}
}