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):

CPU$0.0001 / second
Nvidia A40$0.0006 / second
Nvidia A100 (40GB)$0.0012 / second
  1. The user who makes the prediction gets charged, not the predictor owner.
  2. Function does not charge for time spent on cold starts.

Team Plans

Deploy AI apps and automations with your team.



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



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



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:

SeatsUp to 38 + $12/seat/moCustom
Active PredictorsUnlimitedUnlimitedUnlimited
Prediction Timeout90 seconds90 secondsCustom
CPU Concurrency100400Custom
GPU Concurrency520Custom
Prediction Payload≤ 10MB≤ 10MBCustom
SupportCommunity DiscordCommunity DiscordPrivate Slack
Warm Predictors1
Multi-GPU Acceleration
Bring your own Cluster
  1. Warm predictors have at least one replica always available, eliminating prediction latency caused by cold starts.

Frequently Asked Questions

Answering a few common questions.