text-embedding-3-small

Embedding modelCard summarized

Improved, more performant version of our ada embedding model

Source: "New embedding models and API updates" launch post and Embeddings guide (no model card published)

Use it via API

$0.02 / 1M tok

Code example Compare

Where to call it

OpenAI APItext-embedding-3-small

Supports

Batch API

Full feature support

Good for

Search (ranking results by relevance to a query)
Clustering and classification of text
Recommendations and anomaly detection

Overview

OpenAI · 01Small

Embed 3 Small

Improved, more performant version of our ada embedding model

Typical price

$0.02 / 1M tok

Text input

Dimensions: 1536
Max input: 8,192 tokens
Modes: text embeddings
Released: 25 Jan 2024

text-embedding-3-small is OpenAI's small, efficient third-generation text embedding model (1536 dimensions by default). OpenAI positions it as an upgrade over text-embedding-ada-002: better scores on multilingual retrieval (MIRACL) and English tasks (MTEB) at one fifth of ada-002's price. Vectors can be shortened with the dimensions parameter. launch post; embeddings guide

text-embedding-3-small

Typical price: $0.02 / 1M tok
Dimensions: 1536 (can be shortened with the dimensions parameter)
Max input: 8,192 tokens
Languages: Multilingual (MIRACL multi-language retrieval reported); no language count stated
Weights: Closed
Released: 25 Jan 2024

text embeddings