Replicate
CuratedAcquiredRun and deploy open models through an API, billed per second; now part of Cloudflare
From
—
GPU from
$0.810/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
4
plans
Overview
Replicate hosts thousands of open-source models behind a simple API and lets developers package their own models with Cog and deploy them on per-second-billed GPUs from T4 to H100/H200. Cloudflare announced its acquisition of Replicate in November 2025 to fold it into the Workers AI platform.
Cloudflare announced the acquisition on 17 November 2025; replicate.com continues to operate.
Plans & prices
GPU instances4
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
Nvidia T4 (gpu-t4) — $0.000225/s | 1× T4 | $0.810 | $0.810 | — | Verified 4 days ago | |
Nvidia L40S (gpu-l40s) — $0.000975/s | 1× L40S | $3.51 | $3.51 | — | Verified 4 days ago | |
Nvidia A100 80GB (gpu-a100-large) — $0.0014/s | 1× A100 80GB | $5.04 | $5.04 | — | Verified 4 days ago | |
Nvidia H100 (gpu-h100) — $0.001525/s | 1× H100 SXM | $5.49 | $5.49 | — | Verified 4 days ago |
GPU models
Similar providers
RunPodDeveloper GPU cloud with per-second Pods, serverless endpoints and community hosts
falGenerative media platform with pay-per-use model APIs and serverless GPUs
ModalPython-native serverless cloud with per-second GPUs from T4 to B300
Hugging FaceAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference
DeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute
Fireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deployments
BasetenInference platform for dedicated model deployments and model APIs, billed per minute
BeamServerless GPUs, sandboxes and BYOC deployments billed by the millisecond