fal
CuratedActiveGenerative media platform with pay-per-use model APIs and serverless GPUs
From
—
GPU from
$4.00/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
6
plans
Overview
fal serves image, video, audio and 3D generation models through pay-per-use APIs on its own optimised inference engine, and rents its GPU fleet (H100 to B300 and GB200) for custom serverless deployments at hourly list prices with committed-use discounts.
Plans & prices
GPU instances6
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
RTX PRO 6000 serverless — list price per GPU | 1× RTX PRO 6000 Blackwell | $4.00 | $4.00 | — | Verified 4 days ago | |
NVIDIA H100 serverless — list price per GPU | 1× H100 SXM | $4.50 | $4.50 | — | Verified 4 days ago | |
NVIDIA H200 serverless — list price per GPU | 1× H200 | $6.00 | $6.00 | — | Verified 4 days ago | |
NVIDIA B200 serverless — list price per GPU | 1× B200 | $7.99 | $7.99 | — | Verified 4 days ago | |
NVIDIA GB200 serverless — list price per GPU | 1× GB200 (Grace Blackwell) | $9.99 | $9.99 | — | Verified 4 days ago | |
NVIDIA B300 serverless — list price per GPU | 1× B300 (Blackwell Ultra) | $12.99 | $12.99 | — | Verified 4 days ago |
GPU models
Similar providers
Together AIOpen-model inference API plus self-serve and reserved NVIDIA GPU clusters
CirrascaleSan Diego AI cloud with NVIDIA, AMD, Qualcomm and Tenstorrent systems on term pricing
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
GMI CloudNVIDIA Cloud Partner renting H100/H200/B200 and GB200 from its own data centers
GroqInference neocloud built on its own LPU accelerators, serving models via GroqCloud