Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Voyage AI - Open weights - verified

Voyage 4 Nano embeddings

Voyage 4 Nano is a current embedding model from Voyage AI, with open weights on Hugging Face at voyageai/voyage-4-nano. It returns 1,024-dimension vectors by default and accepts up to 32,000 input tokens, for text input. There is no API price: the weights download from Hugging Face under Apache 2.0, and you pay for the compute you run them on.

CurrentModel id: voyageai/voyage-4-nano- weights: voyageai/voyage-4-nano

Default dims
1,024
Max input
32,000 tok
Price / 1M
Self-hosted
Inputs
Text

Dimensions

Flexible output size
  • 2,048
  • 1,024default
  • 512
  • 256

Default output: 1,024 dimensions.

Listed sizes: 2,048, 1,024, 512 and 256.

Voyage AI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

Pricing

No API price: the weights are on Hugging Face and you run them on your own hardware or host.

Open weights

Hugging Face repo
voyageai/voyage-4-nano
License
Apache 2.0apache-2.0
Commercial use
Commercial use allowedCommercial use is allowed, per the license.
Parameters
346M (346,451,968)

Worth knowing

Voyage docs list 1024 as the API default while the Hugging Face card says the Sentence Transformers default is 2048, and embeddings are compatible with the rest of the Voyage 4 series.

Release date not stated in the sources. Multilingual: yes.

Usage

Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.

Python
from sentence_transformers import SentenceTransformer
import torch

# Standard loading, assuming no GPU access
model = SentenceTransformer(
    "voyageai/voyage-4-nano",
    trust_remote_code=True,
    truncate_dim=2048
)

Source: huggingface.co/voyageai/voyage-4-nano

FAQ

How many dimensions does Voyage 4 Nano output?

Default output: 1,024 dimensions. Listed sizes: 2,048, 1,024, 512 and 256. Voyage AI documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

What is the max input length of Voyage 4 Nano?

32,000 tokens per input, per the model card. Longer text has to be chunked before you embed it.

Can I use Voyage 4 Nano commercially?

Voyage 4 Nano is released under Apache 2.0, and commercial use is allowed. The license text is at https://huggingface.co/voyageai/voyage-4-nano.

What can Voyage 4 Nano embed?

Text input, per the provider. It is documented as multilingual.

Sources

Last verified from the pages below.

More Voyage AI embedding models

Default dimensions, max input tokens and list price per 1M tokens.

All embedding models - Open-weight embedding models

Newsletter

New models, every week

One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.

Keep exploring

Model API pricing and specs

First-party prices per 1M tokens for chat and reasoning models.

Local models

Open-weight LLMs you can download and run, with sizes and licenses.

What is RAG?

Where embeddings fit in a retrieval pipeline, end to end.

Vector databases compared

Where the vectors go once you have picked a model.