Run Nomic Embed v1.5
Ready in about 90 seconds. No install, no setup. From $0.22 per hour.
What it does
This model converts text into numbers that capture what the text means. Documents about the same subject end up close together, even when they share no words.
That is what powers search that understands "how do I get my money back" and returns the refund policy, and it is the first step in any system that answers questions from your own documents.
You run it once over your archive, store the result, and search it from then on without touching a GPU again.
What you can ask it
50,000 support articles and past tickets.
You get backA searchable index where a plain question finds the right article.
Ten years of company documents.
You get backSearch that works even when nobody remembers the file name.
A product catalog with inconsistent descriptions.
You get backSimilar-product matching that ignores how each entry was worded.
Your setup
We run this on an RTX 3090. It processes about 900 documents per second, so 50,000 documents take under a minute. $0.22 per hour, billed by the minute.
Why this card?
The model is 137 million parameters, small enough that the card is never the constraint. Almost all the time in an embedding job goes on reading the files and writing the results, not on the model. Paying for a faster card would change the total by seconds, so we use the cheapest one in the fleet.
- Memory
- 24GB
- Speed
- about 1 second per thousand documents
- Rate
- $0.22/hr
What will it cost you?
Billed by the minute on a RTX 3090 at $0.22 per hour. A batch job shuts the GPU off when the last thousand documents is done, so this is the whole cost.
Two ways to run it
Click and use it
Upload a sample, run a few test searches, check the quality before committing.
Get early access Best for exploring.Hand us the whole pile
The normal mode. Point at a folder or a database export, collect the index.
Join the list Best for volume. The GPU shuts off automatically when it is done.Model facts
| Parameters | 137M |
|---|---|
| License | Apache 2.0 |
| Memory required | 4GB minimum |
| Base model | Trained from scratch by Nomic AI |
| Publisher | Nomic AI |
| Recommended hardware | RTX 3090, 24GB |
| Hugging Face | nomic-ai/nomic-embed-text-v1.5 |
Want Nomic Embed v1.5 the day it opens?
We are testing the rental flow with a small group first. Leave an email and we will tell you when Nomic Embed v1.5 is ready to run. One message, no newsletter.
Nomic Embed v1.5 questions
Do I need to install anything to use Nomic Embed v1.5?
No. We start a machine with Nomic Embed v1.5 already loaded and hand you a link. Everything runs in your browser, there is nothing to download, and nothing is left on your computer afterwards. It works the same on a Mac, a Windows laptop, or a Chromebook. A workspace is usually ready in about 90 seconds.
How much does it cost to run 50 thousand documents?
About under $0.01. Nomic Embed v1.5 takes about 1 second per thousand documents on the RTX 3090 we recommend, so 50 thousand documents is roughly 55 seconds of GPU time at $0.22 per hour. Billing is by the minute, and a batch job shuts the GPU off the moment the last item finishes. The calculator above works this out for your own numbers.
Can I run Nomic Embed v1.5 on a cheaper card?
Sometimes, and the calculator will not always make it look worth it. The model is 137 million parameters, small enough that the card is never the constraint. Almost all the time in an embedding job goes on reading the files and writing the results, not on the model. Paying for a faster card would change the total by seconds, so we use the cheapest one in the fleet. If you want to try a different card anyway, the advanced catalog lets you pick one and shows the estimated time before you commit.
Can I use Nomic Embed v1.5 commercially?
Yes. Nomic Embed v1.5 is released under the Apache 2.0 license, which permits commercial use with no conditions worth worrying about. You can use the output in paid client work and in products you sell.
What happens to my files after I stop?
Anything you save into your workspace folder stays in your account and is there when you come back. Everything else is destroyed: the machine is terminated and its disk is wiped. Batch job inputs and outputs are deleted from our storage 24 hours after you download them. We do not read your files or use them to train anything.
What if it fails partway through?
You are not charged for work that did not complete, and failed sessions are refunded automatically. Batch jobs write each output as it finishes rather than at the end, so a failure at item 380 of 400 leaves you 379 usable files and a message saying what broke. Restarting picks up where it stopped rather than redoing the work.
Own a GPU that sits idle? Put it to work. The average provider earns $180 to $420 per month per card.
List your GPU