OpenAI text-embedding-3-small

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

VdelaveRazpoložljivo

od 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.

Preizkusi Pridobi API ključ Primerjaj

Cena: 0,024 $/1M vhod
Kontekst: 8191 žetonov
Vhod → Izhod: Besedilo → Vektor
Razvijalec: OpenAI
Posodobljeno: 23. september 2026

Igrišče

Preizkusi OpenAI text-embedding-3-small

Vnos in rezultat

0,024 $/1M vhod

Vhod

0 / 32.000

Primerjaj z (izbirno)

Zažene model dvakrat (obračunano dvakrat).

⌘/Ctrl + Enter

Rezultat

Vektor se pojavi tukaj.

Ta zagon

Cena se pojavi, ko je vnos popoln.

Novo tukaj?

10 brezplačnih kreditov (0,10 $) ob prijavi z Googlom

Uporabno 24 ur po prijavi, do 5 zaganom na dan in največ 2 kreditov na zagon. Druge metode prijave se začnejo brez kreditov.

O OpenAI text-embedding-3-small

PovzetekOd 23. september 2026

OpenAI text-embedding-3-small je model razvijalca OpenAI iz kategorije Vdelave. Na Railwail stane OpenAI text-embedding-3-small 0,024 $ / 1M vhodnih žetonov. Kontekstno okno vsebuje 8191 žetonov.

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.

Ozadje

O OpenAI

Ustanovljeno 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.

Obiščite OpenAI

Arhitektura

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.

Parametri: Undisclosed (smaller than text-embedding-3-large)
Kontekst: 8191 žetonov

Zmožnosti

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

Usposabljanje in licenca

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

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

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

Znane omejitve

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

Raziskovalni članki

Cene

Cene v ameriških dolarjih. Uporaba se obračuna iz vnaprej plačanih kreditov.

Vhod	0,024 $ / 1M žetonov

Obračunani so žetoni, ki jih vsak zahtevek dejansko porabi.
1 kredit = 0,01 $

Kalkulator stroškov

Kalkulator cen

Vhodnih žetonov

/ zapr.

Izhodnih žetonov

/ zapr.

Zahtevki

Skupaj

0,01 $

1 kreditov

Na zahtevek

0,0001 $ · 0,01 kreditov

Vsak zahtevek se zaokroži navzgor na 0,01 kredita.

API

Pokličite OpenAI text-embedding-3-small s svojim Railwail API ključem. V zahtevku uporabite to ID modela:

text-embedding-3-smallDokumentacija API Pridobite API ključ

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);

Nastavite ključ kot RAILWAIL_API_KEYUstvari API ključ

Specifikacije

ID modela: text-embedding-3-small
Razvijalec: OpenAI
Kategorija: Vdelave
Vhod: Besedilo
Izhod: Vektor
Kontekstno okno: 8191 žetonov
Obračunavanje: Po porabi (žetoni ali čas GPU)
Velikost modela: Undisclosed (smaller than text-embedding-3-large)
Licenca: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.
Kataložni vnos posodobljen: 23. september 2026

Vhodne parametre

Vhodi in nastavitve iz vhodne sheme modela. Primer v razdelku API prikazuje, katere od njih API sprejema.

ParameterTipPrivzetoDovoljene vrednosti

inputObvezno
Text to embed (single string or array of strings)
Tip: Besedilo
Privzeto: –
Dovoljene vrednosti: Do 32.000 znakov
dimensions
Tip: Celo število
Privzeto: 1536
Dovoljene vrednosti: 64 do 1536
encoding_format
Tip: Izbira
Privzeto: float
Dovoljene vrednosti: float ali base64

Oznake

openai
embedding
retrieval
rag
matryoshka
general

Primeri pozivov

Primeri iz kataloga Railwail. Niso bili generirani v živo na tej strani.

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

Primeri uporabe

Kaj se uporablja za

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

Povezani vodniki

Embedding Models for Search & Science

Vsi modeli v Vdelave

Pogosta vprašanja

Kaj je OpenAI text-embedding-3-small?

OpenAI text-embedding-3-small je model podjetja OpenAI iz kategorije Vdelave. Na Railwailu ga lahko pokličete z ključem API prek Railwailovega API-ja.

Koliko stane OpenAI text-embedding-3-small na Railwailu?

Na Railwail stane OpenAI text-embedding-3-small 0,024 $ / 1M vhodnih žetonov. Zaračunano vam je tisto, kar vsaka zahteva dejansko porabi. Uporaba se plača s predplačanimi krediti; 1 kredit je enak 0,01 $.

Kako veliko je kontekstno okno OpenAI text-embedding-3-small?

Kontekstno okno OpenAI text-embedding-3-small vsebuje 8191 žetonov.

Kako hiter je OpenAI text-embedding-3-small?

Za OpenAI text-embedding-3-small je na Railwailu še premalo izmerjenih zagonov, da bi navedli čas izvajanja. Odvisno je od vnosa, nastavitev in obremenitve pri ponudniku.

Je OpenAI text-embedding-3-small boljši od OpenAI text-embedding-3-large?

To je odvisno od naloge. OpenAI text-embedding-3-small (OpenAI) in OpenAI text-embedding-3-large (OpenAI) sta oba modela iz kategorije Vdelave. Stran za primerjavo prikazuje njune cene in specifikacije drug ob drugem.

Primerjaj OpenAI text-embedding-3-small in OpenAI text-embedding-3-large

Kako uporabljam OpenAI text-embedding-3-small prek API-ja?

Ustvarite ključ Railwailovega API-ja in pošljite zahtevo z ID-jem modela text-embedding-3-small. Primeri kode za curl, Python in JavaScript so v razdelku API na tej strani.

Primerljivi modeli

Vsi v tej kategoriji

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 vhod
550 % dražje na enoto
Primerjaj OpenAI text-embedding-3-small in OpenAI text-embedding-3-large

Uporabite OpenAI text-embedding-3-small prek API

En API ključ za vsak model na Railwail. Uporaba se obračuna iz vnaprej plačanih kreditov, 1 kredit = 0,01 $.

Pridobite API ključ Oglejte si vse modele