Pass IndexThe State of AISign in

text-embedding-3-small

A small embedding model, an improved and more performant version of the ada embedding model; embeddings numerically represent text for search, clustering, recommendations, anomaly detection, and classification.

text → embedding · made by OpenAI

$0.02per Mtok in
OpenAI · 5 sellers

Sold by 5 ways

SellerLaneRate
Microsoft Azure AI cloudstandard$0.02per Mtok inmodels.dev · read 2026-09-16
OpenAI apistandard$0.02per Mtok indevelopers.openai.com · read 2026-08-24
ElectronHub aggregatorstandard$0.02per Mtok inapi.electronhub.ai · read 2026-09-16
Nous Research aggregatorstandard$0.02per Mtok ininference-api.nousresearch.com · read 2026-08-25
Vercel AI Gateway aggregatorstandard$0.02per Mtok inai-gateway.vercel.sh · read 2026-08-25

About

text-embedding-3-small — a vectors model from OpenAI, sold by 5 companies from $0.02 per Mtok in.

It takes text and returns vectors, with a context window of 8,192 tokens. It was published in January 2024, trained on material up to January 2024. The catalogue files it under embedding. Five companies sell it. The cheapest is $0.02 per Mtok in at ElectronHub.

Every current figure

Maker
OpenAI
Register
model
Takes
text
Returns
embedding
Context
8,192 tokens
Longest answer
1,536 tokens
Published
January 2024
Knowledge to
January 2024
Licence
not read
Sellers
5
Price
$0.02 per Mtok in — ElectronHub

Known as 1 name

openai/text-embedding-3-small