What is voyage-4-lite and what is it good for?

voyage-4-lite is a lightweight, low-cost text embedding model. Typical uses are high-volume semantic search, retrieval for chatbots, clustering and deduplication.

What context window does voyage-4-lite have?

It accepts up to 32K tokens per input.

How do I access voyage-4-lite from inside Iran?

Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Is voyage-4-lite compatible with the OpenAI embeddings API?

Yes. Call the /v1/embeddings endpoint on Hormouz with your Hormouz key, using the same request shape as the OpenAI SDK.

VoyageAI by MongoDB: voyage-4-lite: AI model

voyage-4-lite is a lightweight, low-cost text embedding model from Voyage AI, with a 32K-token context. Reachable from inside Iran through Hormouz.

Context window:: 32,000 tokens
Input:: $0.02/1M tokens
Output:: $0/1M tokens
Type:: embedding

Embeddings

voyage-4-lite is the lightweight general-purpose embedding model of Voyage AI's voyage-4 family, tuned for low latency and low cost. It supports embeddings in 2048, 1024, 512 and 256 dimensions with several quantisation options, so large indexes stay small and fast.

The model handles up to 32K tokens of input per request. Through Hormouz it is served behind an OpenAI-compatible embeddings API: point your base URL at Hormouz and drop in a Hormouz key. Pricing is usage-based at $0.02 per million input tokens. There is no fixed monthly fee.

Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings in 2048, 1024, 512, and 256 dimensions,...

Quickstart

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"voyageai/voyage-4-lite","input":"The quick brown fox"}'

Specs

Vendor	Voyage AI
Type	Embedding
Context window	32,000 tokens
Pricing	$0.02/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":"voyageai/voyage-4-lite","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="voyageai/voyage-4-lite", 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: "voyageai/voyage-4-lite",
  input: "The quick brown fox",
});
console.log(resp.data[0].embedding);

Buy the VoyageAI by MongoDB: voyage-4-lite API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches VoyageAI by MongoDB: voyage-4-lite 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

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 is voyage-4-lite and what is it good for?: voyage-4-lite is a lightweight, low-cost text embedding model. Typical uses are high-volume semantic search, retrieval for chatbots, clustering and deduplication.
What context window does voyage-4-lite have?: It accepts up to 32K tokens per input.
How much does voyage-4-lite cost?: Pricing is usage-based at $0.02 per million input tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access voyage-4-lite from inside Iran?: Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is voyage-4-lite compatible with the OpenAI embeddings API?: Yes. Call the /v1/embeddings endpoint on Hormouz with your Hormouz key, using the same request shape as the OpenAI SDK.

Updated 2026-10-13