Deploy Carrot in ~10 seconds.

Use our 1-click Carrot model or customize your own version.

How to Deploy Whisper

Video tutorial demonstrating how to deploy Whisper to serverless GPUs.

What is Carrot?

Carrot is a cutting-edge vision-language model that performs general-purpose image captioning, image question and answering, and image classification.

Carrot is a significant leap forward in the capabilities of computer vision. Using Carrot, you can identify anything using natural English prompts - similar to GPT-3.

Carrot Demo

Generated Caption:
”A group of people with their horses on the side of a hill next to a mountain covered in mounds of dirt with the top of a volcano visible into the sky above.”

Question: What objects are all in the image?
Answer: horses, people
Question: How many horses are there in the image? Answer: 10
Question: Is someone at the risk of falling?
Answer: no

Deploy Carrot on Serverless GPUs.

It's never been more affordable to build with ML models.

Deploy Now Read Docs

Serverless Pricing

Only pay for the resources you use. That's the power of Banana.

Usage Pricing

Only pay for GPU compute you use

$.00051992/second

1 hour of FREE credits 💸
Run on A100 GPUs
ML Models up to 16GB
Network Payload up to 50MB
Autoscaling
Spike Tolerance (up to 25 replicas)

Volume Pricing

Prepaid hosting credits at discount

10-40%/off usage rate

Everything in Usage Pricing
Minimum purchase of $1,000
More you buy = more you save
Dedicated SLA Response Time
Increased Spike Tolerance (25+ replicas)

Code editor graphic with the lines of code needed to deploy machine learning on Banana.

What does Banana do?

Banana provides inference hosting for ML models in three easy steps and a single line of code.

Deploy models to production faster and cheaper with our serverless GPUs than developing the infrastructure yourself.

Why use Serverless GPUs?

Ready to Scale

When you need to scale bi-directionally based on demand and keep a great customer experience.

Cost Savings

When you need to gain cost efficiency and your spend for “always-on” GPUs is too expensive.

Speed to Market

When you need a reliable hosting solution quickly and/or prefer moving fast over building in-house.