Flexible Pricing for ComfyUI Online & ComfyUI API Inference

Run ComfyUI Online effortlessly with our cloud GPUs or deploy production-ready AI with the ComfyUI API. Choose the right plan for your workflow needs.
Individual
$0/mo (Pay-As-You-Go)
Hobbyists, testing, occasional users
Start Using ComfyUI Online
Run ComfyUI Online instantly
Any Model, Any Node
GPU rental by the minute
Basic ComfyUI API Deployment
Live Chat Support
Pro
Coming Soon!
$20 / Seat
Small businesses, frequent users
Join the Waitlist for Pro
Lower GPU pricing with monthly plan
Teams and user managment
Scalable ComfyUI API with priority access
Basic privacy controls
Entreprise
Custom
Enterprises, high-scale apps
Contact Sales
Fixed cost per inference
100s of concurrent ComfyUI API calls
Custom privacy & retention policies
Dedicated support & SLA
Custom contract & enterprise features

GPU Pricing

Choose the right GPU for your ComfyUI Online or ComfyUI API workflows based on performance and cost. Need help deciding? Read our guide on picking the right GPU for ComfyUI to find the best option for your use case.

GPU

24GB VRAM

Specifications

Hourly Cost

A5000
RTX 4090
A40
24GB VRAM
Performance
48GB VRAM
80GB VRAM
80GB VRAM
Performance
48GB VRAM
Performance
$0.60
$1.20
$0.70
$1.60
$2.50
$4.00
L40
A100
H100

Serverless API Pricing

With the API, you only pay for the time your workflow is running—no idle costs, no wasted compute. Scale seamlessly while keeping costs predictable.  Learn more about how API pricing works in our help article.

GPU

24GB VRAM

Specifications

Cost per Second

Small
Medium
Large
48GB VRAM
80GB VRAM
$0.0005
$0.0007
$0.0025

Bring Your Creative Team into the Future

From concept to delivery, InstaSD empowers your team to create, deploy, and monetize AI-driven visual assets seamlessly. Start streamlining your creative process today.