opendunes

Embed V1 4B

by PerplexityReleased 16 March 2026

Embed V1 4B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 2,560 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the larger model of the pair, tuned for the best result quality.

TakesText
GivesEmbeddings
Create API keyCompare

What it costs

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

≈ 0,010 DA per page3 000 DA buys about 300 000 pages

One page, the ordinary use

1 000 tokens sent× 9,99 DA per 1M0,010 DA
Total≈ 0,010 DA

Every rate

Meter↑ you send↓ comes back
Text tokens9,99 DA

per 1M tokens

Embed a search query≈ 0,00020 DA
Index a 10-page help centre≈ 0,070 DA
Embed 1 000 product titles≈ 0,15 DA
Index a 50-page product manual≈ 0,35 DA
Index 1 000 web pages≈ 14,99 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.

Perplexity…
↑ text
9,99 DA
Latency
…
Provider↑ textLatencyUptime
Perplexity9,99 DA……

You pay the price of the provider that served your request. Prices read 15:19 · 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
perplexity/pplx-embed-v1-4b
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="perplexity/pplx-embed-v1-4b",
    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 Embed V1 4B

  • How much does Embed V1 4B cost in dinars?

    About 0,010 DA per page. ↑ 9,99 DA per 1M tokens.

  • Is Embed V1 4B 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 Embed V1 4B best for?

    Embed V1 4B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 2,560 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the larger model of the pair, tuned for the best result quality.

  • Embed V1 4B or Embed V1 0.6B?

    Embed V1 0.6B costs 0,0087 DA less for the same page.

  • How do I pay for Embed V1 4B without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Embed V1 4B included, is paid from that balance. No foreign card, no conversion.

  • Does Embed V1 4B work in Arabic, French or Darja?

    Perplexity tags the model as multilingual but names no languages. Arabic, French and Darja are not named.

  • How much text in one input?

    Up to 32 000 tokens. Split anything longer.

  • How many dimensions?

    Not stated.

  • Who makes Embed V1 4B, and when was it released?

    Perplexity. Released 16 March 2026.

Other Perplexity models, priced in dinars

See all Perplexity models
Decider V1.2Perplexity · Oct 16, 2026

Decider V1.2 does not write text. You send content as text, a table of data or a picture, plus named questions of three kinds: yes or no, a choice among as many as 255 options, or a score on an ordered scale. It returns the probability of every answer, so your own system sets its thresholds for sorting, routing or moderation. It is the larger model of the pair and reads about 262 pages; Decider Flash V1.2 is the smaller, lower-cost version.

262 pages per call
≈0,0067 DAper case
View model
Embed V1 0.6BPerplexity · Mar 16, 2026

Embed V1 0.6B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 1,024 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the small, quick model of the pair.

32 pages per call
≈0,0013 DAper page
View model
Decider Flash V1.2Perplexity · Oct 16, 2026

Decider Flash V1.2 does not write text. You send content as text, a table of data or a picture, plus named questions: yes or no, a choice among as many as 255 options, or a score on an ordered scale. It returns a probability for every answer, so your own system sets its thresholds for sorting, routing or moderating high volumes.

262 pages per call
≈0,0033 DAper case
View model
SonarPerplexity · Jan 27, 2025

Sonar answers a question with a web search behind it: you send text or a picture and get a written answer with citations, and you can choose which sources it draws on. It keeps about 127 pages in mind at once and is the lightest, fastest model of the Sonar line, meant for question-and-answer features inside an app.

Searches the web120 pages at once
≈2,16 DAper message
View model