Embeddings API

Generate vector embeddings for text. Compatible with the OpenAI Embeddings API.

Base URL

https://api.getkawai.com/v1

Authentication

When authentication is enabled, include your token in the Authorization header:

Authorization: Bearer API_KEY

Embeddings

Create vector embeddings for semantic search and similarity.

POST /embeddings

Create embeddings for the given input text. The model must support embedding generation.

Authentication: Required when auth is enabled. Uses wallet-based API keys.

Headers

Header	Required	Description
Authorization	Yes	Bearer token for authentication
Content-Type	Yes	Must be application/json

Request Body

Content-Type: application/json

Field	Type	Required	Description
model	string	Yes	Embedding model ID (e.g., 'embeddinggemma-300m-qat-Q8_0')
input	string|array	Yes	Text to generate embeddings for. Can be a string or array of strings.
dimensions	integer	No	Reduce output to first N dimensions (for Matryoshka models). Must be <= model's native dimensions.

Response

Returns an embedding object with vector data.

Content-Type: application/json

Examples

Generate embeddings for text:

curl -X POST https://api.getkawai.com/v1/embeddings \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "embeddinggemma-300m-qat-Q8_0",
    "input": "Why is the sky blue?"
  }'

---