Graphene

01/ Pricing

Pay for the GPU-seconds you run.

Serverless inference bills per GPU-second while your code is on the GPU. Queue, scheduling, and prepare time are not charged. Training mode bills at the underlying GCP VM rate.

Reference ratesSnapshot from dev catalog; log in for live values

GPU	VRAM	/ sec	/ hr	Inference	Train
NVIDIA T4t4	16 GB	$0.000223	$0.80	Warm pool	Supported
NVIDIA L4l4	24 GB	$0.000358	$1.29	Warm pool	Supported
NVIDIA A100 40 GBa100-40g	40 GB	$0.001630	$5.87	Warm pool	Supported
NVIDIA H100h100	80 GB	$0.005440	$19.58	Warm pool	Supported

02/ Plans

Three plans. Zero hidden fees.

Starter

/Personal workspace
/Pay per GPU-second
/CLI and agent SDK
/Community support

Get Started

Team

$TBD

/ month

/Shared workspace (coming soon)
/Priority inference warm pool
/Usage export
/SLA response

Enterprise

Custom

/Dedicated nodes
/Commit discounts
/SSO and audit log (roadmap)
/Named support

Talk to us

03/ Notes

Billing pipeline (invoices, auto-recharge, spend-limit) ships after the v1 console. Current run summary shows a demo charge calculated client-side from the rates above.