fal Serverless
Runs a customer's own model or app on fal's GPU fleet, billed by the hour rather than per generation.
Find alternatives to fal Serverless
Per GPU-hour, from $1.89 for an H100; no seat fee and no minimum.
What it does
- GPU cloud
- Model hosting
Sources
- Pricing
- Sold within
-
fal's documentation states "Serverless access is approved per account. A fal account is free. To deploy your own apps on fal Serverless, the fal team must approve access for your account." GPU rates are published ("as low as $1.89/hr for H100"), but deploying is gated on that approval.
Also from Fal
-
fal Model API
Hosted API that runs image, video and audio generation models, billed by compute time.
-
fal Agent AI agent
Subscription agent that plans and runs image and video generation across fal's hosted models, from first frame to final delivery.
Something wrong here? Send a correction — quote this product id: fal-serverless.