Run Codestral 22B

Ready in about 90 seconds. No install, no setup. From $0.45 per hour.

SOC 2 controls 142 verified providers 99.2% uptime Ready in about 90 seconds

What it does

Codestral was trained for a task most coding models handle badly: writing the missing piece when there is code both above and below the gap.

That is what editor completion actually is, and it is why Codestral often feels better in an editor than a larger general model.

The license is restrictive. It is free for personal use, research, and testing, but not for commercial products or internal business use without a paid license from Mistral.

What you can ask it

You give it

Fill in the body of this function, with code above and below it.

You get back

An implementation that matches the surrounding style and variable names.

You give it

Complete this partially written SQL query.

You get back

A finished query consistent with the schema it can see.

You give it

Add the missing error handling branch.

You get back

A branch matching the error style used elsewhere in the file.

Your setup

WE RUN THIS ON RTX 4090

We run this on an RTX 4090. It writes at about 60 tokens per second with roughly 32,000 tokens of surrounding code in context. $0.45 per hour, billed by the minute.

Why this card?

At 22 billion parameters the 4-bit version is about 13GB, leaving around 10GB on a 24GB card for context. Fill-in-the-middle work needs less context than a chat assistant, because the useful signal is the code immediately around the gap rather than the whole repository, so this is a comfortable fit rather than a tight one.

Memory
24GB
Speed
about 2 minutes per thousand lines
Rate
$0.45/hr

What will it cost you?

30 thousand lines written 68 minutes $0.51

Billed by the minute on a RTX 4090 at $0.45 per hour. A batch job shuts the GPU off when the last thousand lines is done, so this is the whole cost.

Two ways to run it

OPEN THE APP

Click and use it

Connect your editor and use it for completion.

Get early access Best for exploring.
RUN A BATCH JOB

Hand us the whole pile

Not the usual mode for this model. Use Qwen2.5-Coder for repository-wide jobs.

Join the list Best for volume. The GPU shuts off automatically when it is done.
244 Codestral 22B jobs run on GPUVault in the last 30 days
Model facts
Parameters22B
LicenseMistral AI Non-Production License
Memory required13GB minimum, 24GB recommended
Base modelTrained from scratch by Mistral AI
PublisherMistral AI
Recommended hardwareRTX 4090, 24GB
Hugging Facemistralai/Codestral-22B-v0.1
COMING SOON

Want Codestral 22B the day it opens?

We are testing the rental flow with a small group first. Leave an email and we will tell you when Codestral 22B is ready to run. One message, no newsletter.

Codestral 22B questions

Can I use Codestral at work?

Not without a paid license. The Mistral AI Non-Production License covers personal projects, research, and evaluation, but explicitly excludes commercial and internal business use. If you are writing code for an employer or a client, use Qwen2.5-Coder 32B or DeepSeek-Coder V2 Lite instead. Both permit commercial use.

Do I need to install anything to use Codestral 22B?

No. We start a machine with Codestral 22B 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 30 thousand lines written?

About $0.51. Codestral 22B takes about 2 minutes per thousand lines on the RTX 4090 we recommend, so 30 thousand lines written is roughly 68 minutes of GPU time at $0.45 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 Codestral 22B on a cheaper card?

Sometimes, and the calculator will not always make it look worth it. At 22 billion parameters the 4-bit version is about 13GB, leaving around 10GB on a 24GB card for context. Fill-in-the-middle work needs less context than a chat assistant, because the useful signal is the code immediately around the gap rather than the whole repository, so this is a comfortable fit rather than a tight one. If you want to try a different card anyway, the advanced catalog lets you pick one and shows the estimated time before you commit.

What are the license restrictions on Codestral 22B?

Codestral 22B is released under the Mistral AI Non-Production License. That is not a permissive license, so read it before you use the output in paid work. We show the license on every model page precisely because this catches people out, and there is usually a permissively licensed alternative in the same category.

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.

Own a GPU that sits idle? Put it to work. The average provider earns $180 to $420 per month per card.

List your GPU