AI / LLM · cost

How much does Replicate cost?

Name: Replicate API
Brand: Replicate

Replicate bills across 15 metered dimensions. The table below lists the current per-unit rates, verified June 14, 2026. What you actually pay depends on your usage volume, which is the number a scan computes for your specific app.

Last verified June 14, 2026Official Replicate pricing

Replicate pricing breakdown

Per-unit pricing by metered dimension.
Metered dimension	Price
CPU (Small)	$0.025 / 1k GPU-seconds
CPU	$0.1 / 1k GPU-seconds
Nvidia T4 GPU	$0.225 / 1k GPU-seconds
Nvidia L40S GPU	$0.975 / 1k GPU-seconds
2x Nvidia L40S GPU	$1.95 / 1k GPU-seconds
Nvidia A100 (80GB) GPU	$1.4 / 1k GPU-seconds
2x Nvidia A100 (80GB) GPU	$2.8 / 1k GPU-seconds
4x Nvidia A100 (80GB) GPU	$5.6 / 1k GPU-seconds
8x Nvidia A100 (80GB) GPU	$0.0112 / GPU-seconds
Nvidia H100 GPU	$1.53 / 1k GPU-seconds
2x Nvidia H100 GPU	$3.05 / 1k GPU-seconds
4x Nvidia H100 GPU	$6.1 / 1k GPU-seconds
8x Nvidia H100 GPU	$0.0122 / GPU-seconds
4x Nvidia L40S GPU	$3.9 / 1k GPU-seconds
8x Nvidia L40S GPU	$7.8 / 1k GPU-seconds

Billed per-second of GPU/CPU time, varies by hardware. Many public models also billed by input/output (e.g. tokens, images, video seconds). Multi-GPU A100/H100/L40S capacity available with committed spend contracts.

Source: replicate.com · Catalog 2026-06-14.2. Confirm the live rate before you commit.

What does Replicate cost inside your app?

The rates above are per unit. Your bill is those rates times how hard your code leans on Replicate, plus everything around it. PrePrice scans your project, finds where you call Replicate, and computes your real cost per user and what to charge.

Find your real cost — free

Replicate cost questions

How is Replicate billed?

Replicate is billed per metered unit of usage. See the table above for each dimension and its rate, and the official pricing page for plan minimums and included allowances.

Why is my Replicate bill higher than expected?

The per-unit rate is only one of the four numbers that set your bill. The others are how much your app uses Replicate, how often, and across how many users. Long prompts, retries, multi-step agents, and uncached repeated context all multiply the rate. PrePrice models that usage from your code so the number is real, not a guess.

Where do these Replicate prices come from?

From Replicate's official pricing page (replicate.com), verified June 14, 2026 and re-checked on a schedule. Pricing changes often, so confirm the live rate before you commit.