Create embeddings

POST

/embeddings

Creates embedding vectors for the input text using an OpenAI-compatible request and response
format. For asymmetric models (for example sionic-ai/comsat-embed-ko-8b-preview) embed
documents as-is and set extra.input_type to query for search queries.

Request

Header Params

Body Params application/jsonRequired

Examples

Document embedding (default)Query embedding

{
    "model": "sionic-ai/comsat-embed-ko-8b-preview",
    "input": "Seoul is the capital of South Korea."
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

cURL

Document embedding (default)Query embedding

curl --location '/embeddings' \
--header 'x-opengateway-user-id;' \
--header 'x-opengateway-session-id;' \
--header 'x-sionic-task-id;' \
--header 'Content-Type: application/json' \
--data '{
    "model": "sionic-ai/comsat-embed-ko-8b-preview",
    "input": "Seoul is the capital of South Korea."
}'

Responses

🟢200OK

application/json

OpenAI-compatible embeddings response.

Bodyapplication/json

Example

{
    "object": "list",
    "data": [
        {
            "object": "embedding",
            "index": 0,
            "embedding": [
                0.0388,
                0.0105,
                -0.003
            ]
        }
    ],
    "model": "sionic-ai/comsat-embed-ko-8b-preview",
    "usage": {
        "prompt_tokens": 7,
        "total_tokens": 7
    }
}

🟠400Bad Request

🟠401Unauthorized

🟠402

🟠429

🔴500Server Error

🔴503Service Unavailable

Modified at 2026-10-27 15:03:30

Create a message (Anthropic Messages format)

Create image