Home Free Tools AI Tools Database OpenAI text-embedding-3

OpenAI text-embedding-3

OpenAI's embedding models

Embeddings $0.02-$0.13 per M tokens
Visit Official Site →

What It Is

OpenAI's text-embedding-3-large and text-embedding-3-small are the industry-standard embedding models. They're the default choice for most RAG systems simply because everyone already has an OpenAI API key. text-embedding-3-large is a 3072-dimensional model that can be shortened to any lower dimension (e.g., 1024, 512) via Matryoshka truncation without significant quality loss.

How It Works

Call the /v1/embeddings endpoint with a text input, get back a dense vector. Supports up to 8191 tokens per request. The Matryoshka property means you can request a smaller dimension via the `dimensions` parameter to save storage in your vector database — useful when you have tens of millions of vectors.

Pricing Breakdown

text-embedding-3-small: $0.02 per M tokens. text-embedding-3-large: $0.13 per M tokens. Batch API offers 50% discount.

Who Uses It

Default choice for RAG applications — thousands of production systems. The 'nobody ever got fired for picking OpenAI embeddings' of the embedding world.

Strengths & Weaknesses

✓ Strengths

  • Industry-standard
  • Matryoshka truncation for storage savings
  • Wide ecosystem support
  • Good retrieval quality

× Weaknesses

  • Not highest-scoring on MTEB
  • Cloud-only (no open weights)
  • Rate limits

Best Use Cases

RAGSemantic searchClusteringClassification

Alternatives

Cohere Embed
Enterprise embedding with compression
Voyage AI
Top-ranked embedding models
BGE (BAAI)
Free open-source embeddings
← Back to AI Tools Database