← Back to all models

text-embedding-3-small

OpenAIEmbeddingProprietary

OpenAI's efficient and affordable embedding model for converting text into 1536-dimensional vectors. Ideal for semantic search, clustering, and RAG with a 5x price reduction over ada-002.

Abilities

Embeddings

Use Cases

RAG / SearchEnterpriseData Analysis

Available in Tools

Availability

How to Use

Use the OpenAI Embeddings API with model `text-embedding-3-small`. Send text and receive vectors up to 1536 dimensions. Supports configurable dimensions (e.g. 512) to trade quality for storage size.

Pros

  • Extremely affordable at $0.02/1M tokens — 5x cheaper than ada-002 and 6.5x cheaper than text-embedding-3-large
  • Better performance than ada-002 despite being much cheaper — 62.3% vs 61.0% MTEB average
  • Configurable dimensions (512–1536) — trade quality for storage and speed
  • Simple API — just send text, receive vectors, no ML expertise needed
  • Up to 8191 tokens input — handles reasonably long text chunks

Cons

  • Lower quality than text-embedding-3-large (62.3% vs 64.6% MTEB) — not ideal when maximum retrieval accuracy matters
  • Closed source — cannot self-host, all data must be sent to OpenAI
  • Cannot fine-tune — stuck with generic embeddings
  • Open-source alternatives (BGE, GTE) approaching comparable quality for free

What to Use It For

star

Perfect For

Cost-effective semantic search at scale

At $0.02/1M tokens it is the cheapest high-quality embedding option from OpenAI — ideal for large document collections

RAG retrieval pipelines on a budget

Good retrieval quality at a fraction of the cost of text-embedding-3-large

thumb_up

Good For

Clustering and classification

Configurable dimensions (512–1536) allow optimizing for speed in clustering workflows

Duplicate detection

Good semantic similarity at low cost makes it practical for deduplication of large collections

warning

Not Recommended

Maximum retrieval accuracy requirements

2.3 percentage points lower MTEB score than text-embedding-3-large — use the large model when accuracy is critical

Try instead: text-embedding-3-large

Processing sensitive data offline

All data must be sent to OpenAI servers — no offline or on-premise option

Try instead: Jina Embeddings v3

block

Do Not Use For

Text generation

Embedding model only — converts text to vectors, cannot generate any text or responses

Try instead: GPT-4o

Fine-tuned domain-specific search

Cannot be fine-tuned — stuck with generic embeddings that may miss domain-specific nuances

Try instead: Jina Embeddings v3

Technical Details

Pricing$0.02 / 1M tokens
ParametersUndisclosed

Links