← Back to CreditFX

Replicate

Hosted model inference (per-model pricing) · GPU Cloud

Representative rate
$5.04/hr

Popular for its huge public model library and one-line API calls — convenience over being the cheapest raw compute option.

All pricing tiers

On-demand (H100)custom · $5.04/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.