POST
/
v1
/
features
/
extractors
/
embed
curl --request POST \
  --url https://api.mixpeek.com/v1/features/extractors/embed \
  --header 'Content-Type: application/json' \
  --data '{
  "type": "url",
  "value": "https://example.com/image.jpg",
  "embedding_model": "image_vector"
}'
{
  "embedding": {
    "vector": [
      123
    ]
  },
  "elapsed_time": 123
}

Headers

Authorization
string | null

Bearer token authentication using your API key. Format: 'Bearer your_api_key'. To get an API key, create an account at mixpeek.com/start and generate a key in your account settings. Example: 'Bearer sk_1234567890abcdef'

Body

application/json
type
enum<string>
required

Type of input to embed

Available options:
url,
text,
file,
base64
embedding_model
enum<string>
required

Name of the vector index to use for embedding

Available options:
image,
openai-clip-vit-base-patch32,
multimodal,
vertex-multimodal,
text,
baai-bge-m3,
keyword,
naver-splade-v3
value
string | null

The input content to embed. Could be a URL, text content, file path, or base64 encoded string

Response

200
application/json
Successful Response
embedding
object
required

The embedding of the processed data, either dense or sparse format

elapsed_time
number | null

The time taken to process the data.