text-embedding-3-large

Overview

text-embedding-3-large is OpenAI's most capable text embedding model, designed for high-performance semantic search and retrieval tasks.

Features

• Supports up to 3,072 dimensions (can be reduced for storage optimization)
• High performance on English tasks with accurate results for most business needs
• Adjustable output size to save storage space while maintaining quality
• The dimensions parameter is only supported in text-embedding-3 and later models
• Superior accuracy compared to previous ada-002 model

Pricing

• $0.13 per million tokens for text-embedding-3-large
• Flexible dimension sizing allows cost optimization