Prediction Pricing
You only pay for the amount of time that your prediction takes.
Function charges1 per second of prediction time2, depending on acceleration (hardware tier):
Acceleration | Price |
---|---|
CPU | $0.0001 / second |
Nvidia A40 | $0.0006 / second |
Nvidia A100 (40GB) | $0.0012 / second |
- The user who makes the prediction gets charged, not the predictor owner.
- Function does not charge for time spent on cold starts.
Team Plans
Deploy AI apps and automations with your team.
Developer
$0
plus usage, per month.
Start building and deploying AI features in your apps.
What's included
- Only pay for usage
- Unlimited predictors
- Up to 3 seats per organization
- Unlimited secrets
Organization
$96
plus usage, per month.
Go from prototype to production with your team.
What's included
- 8 seats + $12/seat/mo
- Increased CPU & GPU concurrency
- Warm predictors: no cold starts
- Multi-GPU acceleration
Enterprise
Custom
Deploy Function across your enterprise, for both internal teams and customers.
What's included
- Deploy Function on-prem
- Bring your own cluster
- Custom number of seats
- Enhanced, private support
Below are features included in each plan:
Developer | Organization | Enterprise | |
---|---|---|---|
Seats | Up to 3 | 8 + $12/seat/mo | Custom |
Active Predictors | Unlimited | Unlimited | Unlimited |
Secrets | Unlimited | Unlimited | Unlimited |
Prediction Timeout | 90 seconds | 90 seconds | Custom |
CPU Concurrency | 100 | 400 | Custom |
GPU Concurrency | 5 | 20 | Custom |
Prediction Payload | ≤ 10MB | ≤ 10MB | Custom |
Support | Community Discord | Community Discord | Private Slack |
Warm Predictors1 | |||
Multi-GPU Acceleration | |||
Bring your own Cluster |
- Warm predictors have at least one replica always available, eliminating prediction latency caused by cold starts.
Frequently Asked Questions
Answering a few common questions.