OpenAI text-embedding-3-small

Name: OpenAI text-embedding-3-small
Brand: OpenAI
SKU: text-embedding-3-small
Price: 0.024 USD
Availability: InStock

EmbeddingsAvailable

by OpenAItext-embedding-3-small

OpenAI's small, low-cost embedding model. Returns 1536-dim vectors by default and supports shortening output dimensions via the dimensions parameter without retraining. Replaced text-embedding-ada-002 with better retrieval quality at a fraction of the price, and is the default choice for general-purpose semantic search and RAG.

Try it Get API key Compare

Price: $0.024/1M in
Context: 8,191 tokens
Input → output: Text → Vector
Developer: OpenAI
Updated: September 23, 2026

Playground

Try OpenAI text-embedding-3-small

Input & output

$0.024/1M in

Input

0 / 32,000

Text to embed (single string or array of strings)

Compare with (optional)

Runs the model twice (billed twice).

⌘/Ctrl + Enter

Output

The vector appears here.

This run

The price appears once the input is complete.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits.

About OpenAI text-embedding-3-small

TL;DRAs of September 23, 2026

OpenAI text-embedding-3-small is a model by OpenAI in the Embeddings category. On Railwail, OpenAI text-embedding-3-small costs $0.024 / 1M input tokens. The context window holds 8,191 tokens.

text-embedding-3-small is the cheaper of OpenAI's third-generation embedding models. It outputs 1536-dim embeddings by default but supports the dimensions parameter, which uses Matryoshka-style truncation so you can request shorter vectors (for example 512 dims) and trade a small amount of accuracy for lower storage and faster similarity search. It scores higher than the older ada-002 on the MTEB benchmark while costing significantly less, which makes it the common default for production retrieval, clustering and classification pipelines. Accepts a single string or a batch of strings per request.

Background

About OpenAI

Founded 2015 · San Francisco, California, USA

OpenAI was founded in December 2015 by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, Wojciech Zaremba and John Schulman and restructured to a capped-profit company in 2019. The embedding line started with text-embedding-ada-001 (2021), was unified into ada-002 (December 2022) and replaced in January 2024 by the v3 generation. text-embedding-3-small is the smaller, cheaper sibling of text-embedding-3-large: it beats ada-002 by ~5 points on MTEB at one fifth the price ($0.00002 per 1k tokens). Together with the large variant it was the first OpenAI embedding model to support Matryoshka-style dimension shortening, allowing callers to choose any vector size between 256 and 1,536 without retraining or quality drop.

Visit OpenAI

Architecture

Transformer bi-encoder with Matryoshka representation learning

OpenAI text-embedding-3-small is the entry-level embedding model in the v3 generation. It produces 1,536-dimensional vectors by default and supports the same Matryoshka shortening as the large variant, so callers can request any dimension between 256 and 1,536 in the API and OpenAI will truncate-and-renormalise on the fly. Maximum input length is 8,191 tokens. Training used a contrastive retrieval objective on a curated multilingual web corpus including search-query/document pairs. The model scores around 62.3% MTEB and 44.0% MIRACL multilingual retrieval, a clear step up from 61.0% / 31.4% for ada-002, while being roughly five times cheaper and faster. It is positioned as the default embedding model for cost-sensitive production RAG and large-scale search. Like all OpenAI models the system is closed-source and hosted only.

Parameters: Undisclosed (smaller than text-embedding-3-large)
Context: 8,191 tokens

Capabilities

1,536-dim vectors with Matryoshka truncation to any 256-1,536 size
8,191-token context window for long-document embedding
Multilingual coverage across 100+ languages
$0.00002 per 1k tokens (~5x cheaper than text-embedding-3-large)
Drop-in upgrade from ada-002 via the same /embeddings endpoint
L2-normalised vectors with cosine similarity
Best for: cost-sensitive RAG, large-scale search, embeddings at high QPS

Training & license

Not disclosed. OpenAI describes a 'curated multilingual web corpus' with search-query/document pairs.

License: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.

Safety testing: Embeddings are not subject to content-filter constraints; OpenAI publishes general bias and fairness statements.

Known limitations

Closed weights, hosted only
Cannot fine-tune the model
Lower MTEB / MIRACL scores than text-embedding-3-large
Multilingual quality below Cohere v3 for some low-resource languages
8,191-token cap may force chunking for long documents

Research papers

Pricing

Prices in US dollars. Usage is charged from prepaid credits.

Input	$0.024 / 1M tokens

Billed by the tokens each request actually uses.
1 credit = $0.01

Cost calculator

Price calculator

Input tokens

/ req.

Output tokens

/ req.

Requests

Total

$0.01

1 credits

Per request

$0.0001 · 0.01 credits

Each request is rounded up to 0.01 credits.

API

Call OpenAI text-embedding-3-small with your Railwail API key. Use this model ID in the request:

text-embedding-3-smallAPI documentation Get an API key

curl https://railwail.com/api/v1/embeddings \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The quick brown fox"
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

res = client.embeddings.create(
    model="text-embedding-3-small",
    input="The quick brown fox",
)

print(len(res.data[0].embedding))

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const res = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: "The quick brown fox"
});

console.log(res.data[0].embedding.length);

Set your key as RAILWAIL_API_KEYCreate API key

Specifications

Model ID: text-embedding-3-small
Developer: OpenAI
Category: Embeddings
Input: Text
Output: Vector
Context window: 8,191 tokens
Billing: By usage (tokens or GPU time)
Model size: Undisclosed (smaller than text-embedding-3-large)
License: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.
Catalog entry updated: September 23, 2026

Input parameters

Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.

ParameterTypeDefaultAllowed values

inputrequired
Text to embed (single string or array of strings)
Type: Text
Default: –
Allowed values: up to 32,000 characters
dimensions
Type: Integer
Default: 1536
Allowed values: 64 to 1,536
encoding_format
Type: Choice
Default: float
Allowed values: float or base64

Example prompts

Examples from the Railwail catalog. They were not generated live on this page.

Semantic Search
How to deploy a Node.js app to production
Document Clustering
Machine learning model training techniques

Use cases

What it is used for

Cost-sensitive production RAG
Large-scale semantic search across millions of documents
Embeddings for high-QPS personalisation pipelines
Clustering and topic discovery at low cost
Embeddings for downstream classification

Related guides

Embedding Models for Search & Science

All models in Embeddings

Frequently asked questions

What is OpenAI text-embedding-3-small?

OpenAI text-embedding-3-small is a model by OpenAI in the Embeddings category. On Railwail you can call it with an API key through the Railwail API.

How much does OpenAI text-embedding-3-small cost on Railwail?

On Railwail, OpenAI text-embedding-3-small costs $0.024 / 1M input tokens. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.

What is the context window of OpenAI text-embedding-3-small?

The context window of OpenAI text-embedding-3-small holds 8,191 tokens.

How fast is OpenAI text-embedding-3-small?

There are not enough measured runs of OpenAI text-embedding-3-small on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is OpenAI text-embedding-3-small better than OpenAI text-embedding-3-large?

That depends on the task. OpenAI text-embedding-3-small (OpenAI) and OpenAI text-embedding-3-large (OpenAI) are both models in the Embeddings category. The comparison page shows their prices and specifications side by side.

Compare OpenAI text-embedding-3-small and OpenAI text-embedding-3-large

How do I use OpenAI text-embedding-3-small through the API?

Create a Railwail API key and send your request with the model ID text-embedding-3-small. Code examples for curl, Python and JavaScript are in the API section of this page.

Comparable models

All in this category

OpenAI text-embedding-3-largeOpenAI
OpenAI's highest-quality embedding model. Returns 3072-dim vectors by default and supports reducing dimensions via the dimensions parameter. Outperforms text-embedding-3-small and the older ada-002 on MTEB and multilingual MIRACL retrieval benchmarks, for cases where accuracy matters more than cost.
$0.156/1M in
550 % more expensive per unit
Compare OpenAI text-embedding-3-small vs. OpenAI text-embedding-3-large

Use OpenAI text-embedding-3-small via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.

Get API key Browse all models