Building blocks · by RunPod

RunPod

Rent cloud graphics-chip machines by the hour, or call ready-made generators.

code → data, deployed · code → link, deployed · text, image → image
Way in
Official APISign up yourself, api key
To start
$none
Runs
In the cloud
Checked
Nov 8, 2026Prices as of that day

What it can do 4

Rent GPU instances by the hourcode → data, deployedRTX 4090 $0.34/h community ($0.89 secure), RTX 5090 $0.69/h, A100 SXM $1.39/h, H100 SXM $2.69/h ($3.99 secure), H200 $3.59/h, B200 $5.98/h
Deploy own model or Python code as an autoscaling GPU endpointcode → link, deployedRTX 4090 $1.34/h, A100 $2.72/h, H100 $5.39/h, B200 $10.79/h (serverless rates)
Call public image endpointstext, image → imageFLUX.1 Schnell $0.0024/MP; Pruna T2I $0.005/request
Call public video endpointstext, image → videoWan 2.2 I2V 720p $0.30 per 5s; Sora 2 I2V $0.40 per 4s

Does the same job

Prices and limits as of Nov 8, 2026, from RunPod’s own pages. They change; check before you rely on them.Not affiliated with RunPod. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.