Embed English v3.0 Image

Embed is the leading multimodal embedding model, acting as an intelligent retrieval engine for semantic search and retrieval-augmented generation (RAG) systems.

Handles Image inputs and outputs.

Pricing

• Text Embeddings: $0.10 / 1M tokens
• Image Embeddings: $0.0001 / 1 Image

Learn more about Embed

Usage Notes

• Embeddings perform best when the text to be embedded is less than 512 tokens.
• You can create up to 96 text embeddings per API call.
• You can create 1 image embedding per API call.
• Documents longer than 500 tokens (including the search query) will be split into multiple chunks, where each chunk counts as a singular document.