opendunes

Gemini Embedding 2 Preview

by GoogleReleased 17 April 2026

The preview build of Google's first multimodal embedding model, placing text and images in one vector space so a written query can find matching pictures and the reverse, with 128 to 3,072 dimensions

TakesTextImagesVideoAudioFiles
GivesEmbeddings
Create API keyCompare

What it costs

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

≈ 0,067 DA per page3 000 DA buys about 45 000 pages

One page, the ordinary use

1 000 tokens sent× 66,57 DA per 1M0,067 DA
Total≈ 0,067 DA

Every rate

Meter↑ you send↓ comes back
Text tokens66,57 DA
Picture tokens149,78 DA
Audio tokens2 163,43 DA

per 1M tokens

Embed a search query≈ 0,0013 DA
Index a 10-page help centre≈ 0,47 DA
Embed 1 000 product titles≈ 1,00 DA
Index a 50-page product manual≈ 2,33 DA
Embed 200 product thumbnails≈ 7,73 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.

Google AI Studio…
↑ text
66,57 DA
↑ image
149,78 DA
↑ audio
2 163,43 DA
Latency
…
Provider↑ text↑ image↑ audioLatencyUptime
Google AI Studio66,57 DA149,78 DA2 163,43 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
google/gemini-embedding-2-preview
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="google/gemini-embedding-2-preview",
    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 Gemini Embedding 2 Preview

  • How much does Gemini Embedding 2 Preview cost in dinars?

    About 0,067 DA per page. ↑ 66,57 DA per 1M tokens.

  • Is Gemini Embedding 2 Preview 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 Gemini Embedding 2 Preview best for?

    The preview build of Google's first multimodal embedding model, placing text and images in one vector space so a written query can find matching pictures and the reverse, with 128 to 3,072 dimensions.

  • Gemini Embedding 2 Preview or Gemini Embedding 2?

    Gemini Embedding 2 costs the same for the same page.

  • How do I pay for Gemini Embedding 2 Preview without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Gemini Embedding 2 Preview included, is paid from that balance. No foreign card, no conversion.

  • Does Gemini Embedding 2 Preview work in Arabic, French or Darja?

    Google says Gemini Embedding 2 works across over 100 languages. Arabic, French and Darja are not named on that page.

  • How much text in one input?

    Up to 8 192 tokens. Split anything longer.

  • How many dimensions?

    Not stated.

  • Who makes Gemini Embedding 2 Preview, and when was it released?

    Google. Released 17 April 2026.

Other Google models, priced in dinars

See all Google models
Gemini Omni 1.2 FlashGoogle · Nov 5, 2026

This model is designed to handle text, pictures, and video inputs, allowing it to read up to 130 pages of content. It specializes in generating and editing video clips, producing outputs that include both text and moving images. What sets this model apart is its native ability to process and generate video content directly. It is not suitable for tasks requiring external tool usage or the creation of structured data formats.

Searches the webThinks first130 pages at once
≈2,00 DAper message
View model
Gemini 3.8 Flash TTSGoogle · Sep 23, 2026

#1 for speech · Gemini 3.8 Flash TTS turns text into speech in 130+ languages with studio-grade acting, regional accents and a voice that stays consistent through long dialogues. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for audiobooks, narration and multi-speaker scenes.

30 voices
≈3,02 DAper paragraph read aloud
View model
Nano Banana 2 (Gemini 3.1 Flash Image)Google · Jun 18, 2026

Nano Banana 2, Google's 3.1 Flash Image model, generates and edits images from a written description and reference pictures, returning images with text. It outputs up to 4K, adds very tall and very wide shapes such as 1:8, and renders text in other languages better. Pick it for production batches of ads, banners and edits.

Up to 14 references4K
≈24,60 DAper image
View model
Gemini Omni 1.1 FlashGoogle · Nov 4, 2026

This model accepts text, pictures, and videos as input, allowing it to read up to 130 pages of content. It specializes in creating and editing video content, converting descriptions or pictures into moving images. A key feature is its ability to search the web for information while processing complex visual data. However, it does not utilize external tools or generate structured data formats.

Searches the webThinks first130 pages at once
≈2,00 DAper message
View model