opendunes

E5-Large-v2

by IntfloatReleased 18 November 2025

E5 Large v2 turns English text, and only English, from single sentences to whole documents, into a fingerprint of its meaning, so search finds text that means the same; it also suits reordering search results. Each input can run to about half a page. Start each search question with "query: " and each stored document with "passage: ", which is how the model was trained.

TakesText
GivesEmbeddings
Create API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,0033 DA per page3 000 DA buys about 900 000 pages

One page, the ordinary use

1 000 tokens sent× 3,33 DA per 1M0,0033 DA
Total≈ 0,0033 DA

Every rate

Meter↑ you send↓ comes back
Text tokens3,33 DA

per 1M tokens

Embed one customer question for search≈ 0,00010 DA
Embed one paragraph of a help article≈ 0,00050 DA
Index a 10-page help centre in short chunks≈ 0,023 DA
Embed 1 000 product titles≈ 0,050 DA
Embed 500 short support messages≈ 0,17 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send.

DeepInfraUnited States…
↑ text
3,33 DA
Latency
…
Provider↑ textLatencyUptime
DeepInfraUnited States3,33 DA……

You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/embeddings
Base URL
https://opendunes.com/v1
Model ID
intfloat/e5-large-v2
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.embeddings.create(
    model="intfloat/e5-large-v2",
    input="Delivery to Oran takes two days.",
)

print(resp.data[0].embedding[:5])
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Questions about E5-Large-v2

  • How much does E5-Large-v2 cost in dinars?

    About 0,0033 DA per page. ↑ 3,33 DA per 1M tokens.

  • Is E5-Large-v2 free? Can I try it?

    No. You pay per use from your balance, with no subscription. Run it once from Call it in code, at the same price.

  • What is E5-Large-v2 best for?

    E5 Large v2 turns English text, and only English, from single sentences to whole documents, into a fingerprint of its meaning, so search finds text that means the same; it also suits reordering search results. Each input can run to about half a page. Start each search question with "query: " and each stored document with "passage: ", which is how the model was trained.

  • How do I pay for E5-Large-v2 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, E5-Large-v2 included, is paid from that balance. No foreign card, no conversion.

  • Does E5-Large-v2 work in Arabic, French or Darja?

    The model card says it only works for English text. Arabic, French and Darja are not supported.

  • How much text in one input?

    Up to 512 tokens. Split anything longer.

  • How many dimensions?

    1 024

  • Who makes E5-Large-v2, and when was it released?

    Intfloat. Released 18 November 2025.

Other Intfloat models, priced in dinars

See all Intfloat models
Multilingual-E5-LargeIntfloat · Nov 18, 2025

Multilingual E5 Large turns text in more than 90 languages into a fingerprint of its meaning, so a question in one language can find a matching passage in another. Use it for search across multilingual libraries and for comparing texts in different languages, with each input up to about half a page. Start questions with "query: " and stored passages with "passage: ". For English-only collections, E5 Large v2 is the English-only model with the same level of detail.

≈0,0033 DAper page
View model
E5-Base-v2Intfloat · Nov 18, 2025

E5 Base v2 turns English text, and only English, into a fingerprint of its meaning, so search finds text that means the same; it also suits comparing texts and grouping similar ones. Each input can run to about half a page. Put "query: " before search questions and "passage: " before the documents you store, as the model was trained that way.

≈0,0017 DAper page
View model