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:

4 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, and on-demand rates over spot or reserved ones, then take the lowest price among those.

Search

Matching is partial and case-insensitive, so results can include entries that do not contain your words exactly. Searching "h100" also returns "H100 NVL", and "reserved" also returns reservations.
Every word you type has to match. "h100 spot" shows only H100s sold on spot.

Transparency and funding

Ads and sponsors: Any paid placements are labeled as sponsored content.
Affiliates: Any affiliate links are indicated to you. We may earn a commission if you click them, but this never influences 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

80GB 4 configs 1x-8x

On-Demand from $5.49

From $5.49 / GPU / hr On-Demand View pricing


1x H100	80GB	13	72GB	On-Demand	$5.49	$5.49	Not reported
2x H100	160GB	26	144GB	On-Demand	$5.49	$10.98	Not reported
4x H100	320GB	52	288GB	On-Demand	$5.49	$21.96	Not reported
8x H100	640GB	104	576GB	On-Demand	$5.49	$43.92	Not reported

Nvidia A100

80GB 4 configs 1x-8x

On-Demand from $5.04

From $5.04 / GPU / hr On-Demand View pricing


1x A100	80GB	10	144GB	On-Demand	$5.04	$5.04	Not reported
2x A100	160GB	20	288GB	On-Demand	$5.04	$10.08	Not reported
4x A100	320GB	40	576GB	On-Demand	$5.04	$20.16	Not reported
8x A100	640GB	80	960GB	On-Demand	$5.04	$40.32	Not reported

Nvidia L40S

48GB 2 configs 1x-2x

On-Demand from $3.51

From $3.51 / GPU / hr On-Demand View pricing


1x L40S	48GB	10	65GB	On-Demand	$3.51	$3.51	Not reported
2x L40S	96GB	20	144GB	On-Demand	$3.51	$7.02	Not reported

Nvidia T4

16GB 1 config 1x

On-Demand from $0.81

From $0.81 / GPU / hr On-Demand View pricing


1x T4	16GB	4	16GB	On-Demand	$0.81	$0.81	Not reported

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning. You can find Replicate's latest pricing here.

Packet·ai

Our sponsor

B200 @ $3.75/h on demand

No contract, no spot interrupts, no cluster minimums

Full root SSH, web dashboard, CI/CD ready

Reserve Now