Replicate

Run AI/ML models without complex infrastructure

Founded in 2019 and acquired by Cloudflare in 2025, Replicate is a platform to train and deploy ML models in the cloud. You can run and fine tune open source models such as Meta's Llama 3, Mistral and Stable Diffusion without having to set up complex infrastructure.

They also feature a collection of generative models shared by the community, which you can run via the web UI or using their REST API.

Example customers include BuzzFeed, Labelbox, PhotoAI, Character.ai, Magnific, Unsplash, HeadshotPro.

Replicate Homepage

What's good about Replicate

Run AI/ML models without having to manage the infrastructure
Excellent web UI to explore and try out models without code
Train and deploy custom models using Cog

Replicate pricing examples

Replicate uses a metered billing model. You only pay as long as your code is running, billed by the second based on the hardware selected.

Replicate GPUs

Here are some of the GPU configurations offered by Replicate:

5 GPU models

How this list works

Order

By GPU model: one card per GPU, the most looked-up models first, then the most widely offered ones.
By configuration: every configuration we track. What you can rent now comes first, and within that one row per GPU model before any repeats, so the opening rows cover the range rather than one model's sizes.

The price on a card

Each card leads with a per GPU per hour rate. We prefer configurations the provider reports as in stock, on-demand rates before reserved or spot, then take the lowest per-GPU rate among those.

Search

We match the GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Nvidia H100

4 configs 1x-8x checked <24h ago

On-Demand from $5.49

From $5.49 / GPU / hr On-Demand Visit website


1x H100 gpu-h100	80GB	13	144GB	On-Demand	$5.49	$5.49	Not reported
2x H100 gpu-h100-2x	160GB	--	--	On-Demand	$5.49	$10.98	Not reported
4x H100 gpu-h100-4x	320GB	--	--	On-Demand	$5.49	$21.96	Not reported
8x H100 gpu-h100-8x	640GB	--	--	On-Demand	$5.49	$43.92	Not reported