OpenAI text-embedding-3-small

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

InnfellingarTiltækt

eftir 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.

Prófaðu það Fáðu API-lykil Bera saman

Verð: 0,024 USD/1M inn
Samhengi: 8.191 tákn
Inntak → úttak: Texti → Vigur
Þróunaraðili: OpenAI
Uppfært: 23. september 2026

Leiksvæði

Prófaðu OpenAI text-embedding-3-small

Inntak og úttak

0,024 USD/1M inn

Inntak

0 / 32.000

Bera saman við (valfrjálst)

Keyrir módel tvisvar (rukkað tvisvar).

⌘/Ctrl + Enter

Niðurstaða

Vigurinn birtist hér.

Þessi keyrsla

Verðið birtist þegar inntakið er lokið.

Nýr hér?

10 ókeypis inneign (0,10 USD) þegar þú skráir þig með Google

Hægt að nota 24 klst. eftir skráningu, allt að 5 keyrslur á dag og að hámarki 2 inneign á keyrslu. Aðrar innskráningaraðferðir byrja án inneignar.

Um OpenAI text-embedding-3-small

StuttlegaFrá og með 23. september 2026

OpenAI text-embedding-3-small er módel frá OpenAI í flokknum Innfellingar. Á Railwail kostar OpenAI text-embedding-3-small 0,024 USD / 1M inntakstákn. Samhengisgluggi geymir 8.191 tákn.

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.

Bakgrunnur

Um OpenAI

Stofnað 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.

Heimsækja OpenAI

Arkitektúr

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.

Breytur: Undisclosed (smaller than text-embedding-3-large)
Samhengi: 8.191 tákn

Geta

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

Þjálfun og leyfi

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

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

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

Þekkt takmörk

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

Rannsókargreinar

Verðlagning

Verð í Bandaríkjadölum. Notkun er rukkuð frá fyrirframgreiddum inneign.

Inntak	0,024 USD / 1M tákn

Reikningsfærðir eru tákn sem hver beiðni notar í raun.
1 inneign = 0,01 USD

Kostnaðarreiknir

Verðreiknir

Inntakstákn

/ beiðni

Úttakstákn

/ beiðni

Beiðnir

Samtals

0,01 USD

1 inneign

Fyrir hverja beiðni

0,0001 USD · 0,01 inneign

Hver beiðni er námunduð upp í 0,01 inneign.

API

Kallaðu OpenAI text-embedding-3-small með Railwail API-lyklinum þínum. Notaðu þessa módel-auðkenningu í beiðninni:

text-embedding-3-smallAPI-skjöl Fáðu API-lykil

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);

Stilltu lykil þinn sem RAILWAIL_API_KEYBúa til API-lykil

Forskriftir

Módel-auðkenni: text-embedding-3-small
Þróunaraðili: OpenAI
Flokkur: Innfellingar
Inntak: Texti
Úttak: Vigur
Samhengisglugginn: 8.191 tákn
Reikningur: Eftir notkun (tókar eða GPU-tími)
Stærð módels: Undisclosed (smaller than text-embedding-3-large)
Leyfi: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.
Vörulistafærsla uppfærð: 23. september 2026

Inntaksbreytur

Inntak og stillingar úr inntakskerfi módelsins. Dæmið í API-hlutanum sýnir hverjar þeirra API samþykkir.

BreytuTegundSjálfgefiðLeyfðir gildir

inputnauðsynlegt
Text to embed (single string or array of strings)
Tegund: Texti
Sjálfgefið: –
Leyfðir gildir: allt að 32.000 stafir
dimensions
Tegund: Heiltala
Sjálfgefið: 1536
Leyfðir gildir: 64 til 1.536
encoding_format
Tegund: Val
Sjálfgefið: float
Leyfðir gildir: float eða base64

Merki

openai
embedding
retrieval
rag
matryoshka
general

Dæmi um leiðsögn

Dæmi úr Railwail-vörulistanum. Þau voru ekki mynduð lifandi á þessari síðu.

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

Notkunartilvik

Það sem það er notað fyrir

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

Tengdar leiðbeiningar

Embedding Models for Search & Science

Öll módel í Innfellingar

Algengar spurningar

Hvað er OpenAI text-embedding-3-small?

OpenAI text-embedding-3-small er módel frá OpenAI í flokknum Innfellingar. Á Railwail geturðu kallað það með API-lykli í gegnum Railwail API.

Hvað kostar OpenAI text-embedding-3-small á Railwail?

Á Railwail kostar OpenAI text-embedding-3-small 0,024 USD / 1M inntakstákn. Þér er rukkað fyrir það sem hver beiðni notar í raun. Notkun er greidd úr fyrirframgreiddum inneign; 1 inneign jafngildir 0,01 USD.

Hversu stór er samhengisgluggi OpenAI text-embedding-3-small?

Samhengisgluggi OpenAI text-embedding-3-small geymir 8.191 tákn.

Hversu hratt er OpenAI text-embedding-3-small?

Það eru ekki nóg mældar keyrslur af OpenAI text-embedding-3-small á Railwail ennþá til að tilgreina keyrslutíma. Það fer eftir inntakinu, stillingum og álagi hjá veitandanum.

Er OpenAI text-embedding-3-small betra en OpenAI text-embedding-3-large?

Það fer eftir verkefninu. OpenAI text-embedding-3-small (OpenAI) og OpenAI text-embedding-3-large (OpenAI) eru bæði módel í flokknum Innfellingar. Samanburðarsíðan sýnir verð og forskriftir þeirra hlið við hlið.

Bera saman OpenAI text-embedding-3-small og OpenAI text-embedding-3-large

Hvernig nota ég OpenAI text-embedding-3-small í gegnum API?

Búðu til Railwail API-lykil og sendu beiðni þína með módel-auðkenninu text-embedding-3-small. Kóðadæmi fyrir curl, Python og JavaScript eru í API-hlutanum á þessari síðu.

Sambærileg módel

Öll í þessum flokki

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 USD/1M inn
550 % dýrara á einingu
Bera OpenAI text-embedding-3-small og OpenAI text-embedding-3-large saman

Notaðu OpenAI text-embedding-3-small í gegnum API

Einn API-lykil fyrir öll módel á Railwail. Notkun er rukkuð frá fyrirframgreiddum inneign, 1 inneign = 0,01 USD.

Fáðu API-lykil Skoðaðu öll módel