Skip to main content
Watch: I Built an AI App Without Leaving Databricks

OpenAI - API - verified

text-embedding-3-small embeddings

text-embedding-3-small is a current embedding model from OpenAI, called by API as text-embedding-3-small. It returns 1,536-dimension vectors by default and accepts up to 8,192 input tokens, for text input. The first-party list price is $0.02 per 1M input tokens.

CurrentModel id: text-embedding-3-small

Default dims
1,536
Max input
8,192 tok
Price / 1M
$0.02
Inputs
Text

Dimensions

Flexible output size
  • 1,536default

Default output: 1,536 dimensions.

OpenAI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

Pricing

Per 1M input tokens
$0.02
Batch, per 1M
Not stated

Standard input price per 1M tokens; no separate Batch embedding rate is listed on the pricing page.

Source: developers.openai.com/api/docs/pricing

Usage

Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.

Python
from openai import OpenAI

client = OpenAI()

response = client.embeddings.create(
    input="Your text string goes here", model="text-embedding-3-small"
)

print(response.data[0].embedding)

Source: developers.openai.com/api/docs/guides/embeddings

Worth knowing

OpenAI's guide notes the v3 embedding models lack knowledge of events after September 2021, and the dimensions parameter shortens vectors without losing their concept-representing properties.

Release date not stated in the sources. Multilingual: not stated.

FAQ

How many dimensions does text-embedding-3-small output?

Default output: 1,536 dimensions. OpenAI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

What is the max input length of text-embedding-3-small?

8,192 tokens per input, per OpenAI's documentation. Longer text has to be chunked before you embed it.

How much does text-embedding-3-small cost?

The first-party list price is $0.02 per 1M input tokens. Standard input price per 1M tokens; no separate Batch embedding rate is listed on the pricing page. Source: https://developers.openai.com/api/docs/pricing.

What can text-embedding-3-small embed?

Text input, per the provider.

Sources

Last verified from the pages below.

More OpenAI embedding models

Default dimensions, max input tokens and list price per 1M tokens.

OpenAI API modelsPrices per 1M tokens, context windows and specs for every OpenAI model in the API registry.

All embedding models

Newsletter

New models, every week

One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.

Keep exploring

Model API pricing and specs

First-party prices per 1M tokens for chat and reasoning models.

Local models

Open-weight LLMs you can download and run, with sizes and licenses.

What is RAG?

Where embeddings fit in a retrieval pipeline, end to end.

Vector databases compared

Where the vectors go once you have picked a model.