OpenAI text-embedding-3-large

Name: OpenAI text-embedding-3-large
Brand: OpenAI
SKU: text-embedding-3-large
Price: 0.156 USD
Availability: InStock

EmbeddingsTilgjengelig

av OpenAItext-embedding-3-large

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.

Prøv det Få API-nøkkel Sammenlign

Pris: 0,156 USD/1M inn
Kontekst: 8 191 tokens
Input → output: Tekst → Vektor
Utvikler: OpenAI
Oppdatert: 23. september 2026

Playground

Prøv OpenAI text-embedding-3-large

Inndata og resultat

0,156 USD/1M inn

Inndata

0 / 32 000

Sammenlign med (valgfritt)

Kjører modellen to ganger (fakturert to ganger).

⌘/Ctrl + Enter

Resultat

Vektoren vises her.

Denne kjøringen

Prisen vises når inndataene er fullstendige.

Ny her?

10 gratis credits (0,10 USD) når du registrerer deg med Google

Kan brukes 24 timer etter registrering, opptil 5 kjøringer per dag og maksimalt 2 credits per kjøring. Andre påloggingsmetoder starter uten credits.

Om OpenAI text-embedding-3-large

Kort sagtPer 23. september 2026

OpenAI text-embedding-3-large er en modell fra OpenAI i kategorien Embeddings. På Railwail koster OpenAI text-embedding-3-large 0,156 USD / 1M inndatatokener. Kontekstvinduet inneholder 8 191 tokens.

text-embedding-3-large is OpenAI's most capable third-generation embedding model. It produces 3072-dim embeddings by default and, like the small variant, supports the dimensions parameter for Matryoshka-style truncation so you can store shorter vectors when needed. It leads OpenAI's lineup on the MTEB English benchmark and on the multilingual MIRACL retrieval benchmark, making it the pick when embedding quality is the priority over price. Use it for high-recall semantic search, deduplication and reranking-style retrieval. Accepts a single string or a batch per request.

Bakgrunn

Om OpenAI

Grunnlagt 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 capped-profit OpenAI LP in 2019. The embedding model family started with text-embedding-ada-001 in 2021, was unified into text-embedding-ada-002 in December 2022 (still the most-used embedding model on Earth at one point) and replaced in January 2024 by text-embedding-3-small and text-embedding-3-large. The v3 release was OpenAI's first to support Matryoshka-style dimension reduction (sale of arbitrary 256-3072 dim vectors from the same model) and beat ada-002 by 20+ percentage points on the MIRACL multilingual retrieval benchmark while costing roughly the same.

Besøk OpenAI

Arkitektur

Transformer bi-encoder with Matryoshka representation learning

OpenAI text-embedding-3-large is the flagship embedding model in the v3 generation. It produces 3,072-dimensional vectors by default with full Matryoshka representation support, so callers can request any dimension between 256 and 3,072 in the API and OpenAI will truncate-and-renormalise without re-running the model. The model accepts up to 8,191 tokens per input and was trained with a contrastive retrieval objective on a curated multilingual web corpus, including search-query/document pairs and large-scale instruction-tuned pairs. It scores 64.6% on MTEB and 54.9% on MIRACL multilingual retrieval, a step up from 61.0% / 31.4% for ada-002. Pricing is $0.00013 per 1k tokens. Output vectors are L2-normalised. Like all OpenAI models the system is closed-source and hosted only. OpenAI has not published a technical paper for the v3 family beyond a launch blog.

Parametere: Undisclosed
Kontekst: 8 191 tokens

Evner

3,072-dim vectors with Matryoshka truncation to any 256-3072 size
8,191-token context window for long-document embedding
Multilingual coverage across 100+ languages
State-of-the-art MIRACL multilingual retrieval (~55%)
L2-normalised vectors with cosine similarity
Drop-in upgrade from ada-002 via the same /embeddings endpoint
Best for: production RAG, multilingual search, retrieval-heavy SaaS

Trening og lisens

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

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

Sikkerhetstesting: Embeddings are not subject to content-filter constraints; OpenAI publishes general bias and fairness statements for the embeddings endpoint.

Kjente begrensninger

Closed weights, hosted only
Cannot fine-tune the model
3,072-dim full vectors are storage-heavy without truncation
Worse-than-Cohere v3 on some low-resource languages
8,191-token cap may force chunking for very long documents

Forskningsartikler

Priser

Priser i amerikanske dollar. Bruk belastes fra forhåndsbetalt kreditt.

Inndata	0,156 USD / 1M tokener

Faktureres etter tokenene som hver forespørsel faktisk bruker.
1 kreditt = 0,01 USD

Kostnadsberegner

Prisberegner

Input-tokens

/ forespørsel

Output-tokens

/ forespørsel

Forespørsler

Totalt

0,02 USD

2 credits

Per forespørsel

0,0002 USD · 0,02 credits

Hver forespørsel rundes opp til 0,01 credits.

API

Ring OpenAI text-embedding-3-large med din Railwail API-nøkkel. Bruk denne modell-IDen i forespørselen:

text-embedding-3-largeAPI-dokumentasjon Få en API-nøkkel

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

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

Sett nøkkelen din som RAILWAIL_API_KEYOpprett API-nøkkel

Spesifikasjoner

Modell-ID: text-embedding-3-large
Utvikler: OpenAI
Kategori: Embeddings
Inndata: Tekst
Utdata: Vektor
Kontekstvindu: 8 191 tokens
Fakturering: Etter bruk (tokens eller GPU-tid)
Modellstørrelse: Undisclosed
Lisens: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.
Katalogoppføring oppdatert: 23. september 2026

Inndataparametere

Inndataer og innstillinger fra modellens inndataskjema. Eksemplet i API-delen viser hvilke av dem APIen godtar.

ParameterTypeStandardTillatte verdier

inputobligatorisk
Text to embed (single string or array of strings)
Type: Tekst
Standard: –
Tillatte verdier: opptil 32 000 tegn
dimensions
Type: Heltall
Standard: 3072
Tillatte verdier: 256 til 3 072
encoding_format
Type: Valg
Standard: float
Tillatte verdier: float eller base64

Merkelapper

openai
embedding
retrieval
rag
matryoshka
multilingual

Eksempelprompts

Eksempler fra Railwail-katalogen. De ble ikke generert live på denne siden.

FAQ Matching
How do I reset my password?
Code Search
React useEffect cleanup function memory leak

Brukstilfeller

Hva det brukes til

Production RAG for ChatGPT-style assistants
Multilingual enterprise search
Semantic deduplication and clustering at scale
Recommendation systems based on text similarity
Embeddings for downstream classification tasks

Relaterte veiledninger

Embedding Models for Search & Science

Alle modeller i Embeddings

Ofte stilte spørsmål

Hva er OpenAI text-embedding-3-large?

OpenAI text-embedding-3-large er en modell fra OpenAI i kategorien Embeddings. På Railwail kan du kalle den med en API-nøkkel gjennom Railwail API.

Hvor mye koster OpenAI text-embedding-3-large på Railwail?

På Railwail koster OpenAI text-embedding-3-large 0,156 USD / 1M inndatatokener. Du betaler for det hver forespørsel faktisk bruker. Bruk betales fra forhåndskjøpte kreditter; 1 kreditt tilsvarer 0,01 USD.

Hvor stort er kontekstvinduet til OpenAI text-embedding-3-large?

Kontekstvinduet til OpenAI text-embedding-3-large inneholder 8 191 tokens.

Hvor rask er OpenAI text-embedding-3-large?

Det finnes ennå ikke nok målte kjøringer av OpenAI text-embedding-3-large på Railwail til å angi en kjøretid. Det avhenger av inndataene, innstillingene og belastningen hos leverandøren.

Er OpenAI text-embedding-3-large bedre enn OpenAI text-embedding-3-small?

Det avhenger av oppgaven. OpenAI text-embedding-3-large (OpenAI) og OpenAI text-embedding-3-small (OpenAI) er begge modeller i kategorien Embeddings. Sammenligningssiden viser prisene og spesifikasjonene deres side ved side.

Sammenlign OpenAI text-embedding-3-large og OpenAI text-embedding-3-small

Hvordan bruker jeg OpenAI text-embedding-3-large gjennom API-en?

Opprett en Railwail API-nøkkel og send forespørselen din med modell-ID-en text-embedding-3-large. Kodeeksempler for curl, Python og JavaScript finnes i API-delen av denne siden.

Sammenlignbare modeller

Alle i denne kategorien

OpenAI text-embedding-3-smallOpenAI
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.
0,024 USD/1M inn
85 % billigere per enhet
Sammenlign OpenAI text-embedding-3-large og OpenAI text-embedding-3-small

Bruk OpenAI text-embedding-3-large via APIen

Én API-nøkkel for alle modeller på Railwail. Bruk belastes fra forhåndsbetalt kreditt, 1 kreditt = 0,01 USD.

Få API-nøkkel Se alle modeller