What does Gemini Embedding 2 Preview do?

It converts text, images, PDFs and files, audio and video into numeric vectors (embeddings) for semantic search, retrieval, clustering and RAG. It does not generate chat text.

What input length does Gemini Embedding 2 Preview support?

Up to 8K tokens per input. Longer documents should be chunked before embedding.

How much does Gemini Embedding 2 Preview cost?

Usage-based pricing: $0.2/M in.

What is Gemini Embedding 2 Preview good for?

Semantic search, retrieval-augmented generation, deduplication, clustering, classification and recommendation over text and images.

How do I access Gemini Embedding 2 Preview from inside Iran?

Create an account on Hormouz and generate an API key. Hormouz provides stable access from inside Iran via an OpenAI-compatible API.

Google: Gemini Embedding 2 Preview: AI model

Gemini Embedding 2 Preview is a Google text-embedding model that maps inputs into dense vectors for semantic search, retrieval and RAG. Up to a 8K-token input, via Hormouz.

Context window:: 8,192 tokens
Input:: $0.2/1M tokens
Output:: $0/1M tokens
Type:: embedding

Embeddings

Gemini Embedding 2 Preview is a Google embedding model that turns text and images into fixed-length numeric vectors. Those vectors place semantically similar inputs close together, which is the foundation for semantic search, clustering, classification, recommendation and retrieval-augmented generation (RAG). It accepts inputs up to 8K tokens.

Because embeddings are precomputed once and then compared cheaply, this model suits high-volume pipelines: index a corpus, embed each incoming query, and rank documents by vector similarity. Its multimodal input lets you embed text and images into a shared space for cross-modal search.

Pricing is usage-based at $0.2/M in. Gemini Embedding 2 Preview is served through Hormouz behind an OpenAI-compatible API, with stable access from inside Iran.

Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...

Quickstart

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-embedding-2-preview","input":"The quick brown fox"}'

Specs

Vendor	Google
Type	Embedding
Context window	8,192 tokens
Pricing	$0.20/M in · $0.00/M out
API	embeddings

Code example

cURL

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-embedding-2-preview","input":"The quick brown fox"}'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
resp = client.embeddings.create(model="google/gemini-embedding-2-preview", input="The quick brown fox")
print(resp.data[0].embedding)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const resp = await client.embeddings.create({
  model: "google/gemini-embedding-2-preview",
  input: "The quick brown fox",
});
console.log(resp.data[0].embedding);

Buy the Google: Gemini Embedding 2 Preview API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Google: Gemini Embedding 2 Preview and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account Buy Gemini API access, paid in rial

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

What does Gemini Embedding 2 Preview do?: It converts text, images, PDFs and files, audio and video into numeric vectors (embeddings) for semantic search, retrieval, clustering and RAG. It does not generate chat text.
What input length does Gemini Embedding 2 Preview support?: Up to 8K tokens per input. Longer documents should be chunked before embedding.
How much does Gemini Embedding 2 Preview cost?: Usage-based pricing: $0.2/M in.
What is Gemini Embedding 2 Preview good for?: Semantic search, retrieval-augmented generation, deduplication, clustering, classification and recommendation over text and images.
How do I access Gemini Embedding 2 Preview from inside Iran?: Create an account on Hormouz and generate an API key. Hormouz provides stable access from inside Iran via an OpenAI-compatible API.

Updated 2026-10-13