Skip to main content

Create text embeddings

POST 
/v1/embeddings

Generates a 384-dimensional embedding vector for the input text using the all-MiniLM-L6-v2 sentence transformer model.

The endpoint supports caching for faster responses and includes rate limiting based on your subscription tier.

Request​

Responses​

Successfully generated embedding

Response Headers
    X-RateLimit-Limit

    Monthly request limit

    X-RateLimit-Remaining

    Remaining requests this month

    X-RateLimit-Reset

    Reset timestamp