Replicate · Pricing Plans
Replicate Plans Pricing
Replicate per-second hardware pricing for running open-source ML models.
Replicate Plans Pricing is the machine-readable pricing-plan profile for Replicate on the APIs.io network, conforming to the API Commons Plans specification.
It defines 4 plans, covering usage-based tiers, with named plans including Nvidia T4 GPU, Nvidia L40S GPU, Nvidia A100 (80GB) GPU, Nvidia H100 GPU.
Tagged areas include AI, ML, and GPU.
4 Plans
API Commons Plans
View Source
AIMLGPU
Plans
Nvidia T4 GPU
usage-based
$0.000225/sec.
Per second (second · usage)
0.000225 USD
- Cheapest GPU option
- Best for small models / batch
Nvidia L40S GPU
usage-based
$0.000975/sec.
Per second (second · usage)
0.000975 USD
- Mid-tier GPU
- Good for image generation
Nvidia A100 (80GB) GPU
usage-based
$0.00140/sec.
Per second (second · usage)
0.001400 USD
- High-performance GPU
- Best for medium-to-large models
Nvidia H100 GPU
usage-based
$0.001525/sec.
Per second (second · usage)
0.001525 USD
- Top-tier GPU
- Best for large models / training