← Back to CreditFX

fal

Hosted generative-model inference · GPU Cloud

Representative rate
$4.2/hr

Built specifically for generative media (image, video, audio) rather than general LLM inference — a real-time-focused alternative to Runway/Fireworks-style hosting.

All pricing tiers

On-demand (H100)custom · $4.2/hr

Only one tier verified so far — more being added over time.

Want to calculate exact usage instead of just the representative rate? Open the full calculator.