Create Vector Embeddings from Text — POST /v1/embeddings

POST /v1/embeddings generates vector embeddings from text for semantic search, clustering, and recommendations. Supports up to 8192 tokens per input.

Use the /v1/embeddings endpoint to generate dense vector representations of text. These embeddings capture semantic meaning, making them ideal for powering semantic search, document clustering, similarity scoring, and recommendation systems — all without requiring task-specific model fine-tuning.

Request

POST https://kiosapi.com/v1/embeddings

Headers

Content-Type · string · required

Must be application/json.

Authorization · string · required

Your API key in the format Bearer sk-xxx.

Request Body

model · string · required

The embedding model to use. Example: text-embedding-3-large.

input · string | array · required

The text to embed. Accepts a single string or an array of strings. Each individual input must not exceed 8192 tokens.

Example Request

cURL

curl https://kiosapi.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "text-embedding-3-large",
    "input": "The weather is beautiful today"
  }'

Python

import openai

openai.api_key = "sk-xxx"
openai.base_url = "https://kiosapi.com/v1/"

response = openai.embeddings.create(
    model="text-embedding-3-large",
    input="The weather is beautiful today"
)

print(response.data[0].embedding[:5])  # First 5 dimensions

Response

The endpoint returns a JSON object containing the embedding vector(s), the model used, and token usage statistics.

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.022425562,
        -0.010263717,
        0.022136442,
        0.015323295,
        -0.0013466021
      ]
    }
  ],
  "model": "text-embedding-3-large",
  "usage": {
    "prompt_tokens": 16,
    "total_tokens": 16
  }
}

Response Fields

object · string

Always "list".

data · array

An array of embedding objects, one per input string.

Show data[] fields

data[].object · string

Always "embedding".

data[].index · integer

The zero-based position of this embedding in the input array.

data[].embedding · array of numbers

The embedding vector — an array of floating-point numbers representing the input text in high-dimensional space.

model · string

The model that was used to generate the embeddings.

usage.prompt_tokens · integer

The number of tokens in the input.

usage.total_tokens · integer

Total tokens processed (equal to prompt_tokens for embedding requests).