Comfy API BETA
Deploy your ComfyUI workflow as a production API. It scales effortlessly with your team or project’s needs.
The fastest way from ComfyUI workflow to production endpoint.
Deploy your ComfyUI workflow as a production API. It scales effortlessly with your team or project’s needs.
Call partner models including Seedance, Minimax H3, Nano Banana, and GPT-Image-2. Access the latest models with a single API key.
result = comfy.models.run(
"seedance/v2-pro",
prompt="aerial dolly shot over a neon reef",
)
result.to_file("reef.mp4")Package custom nodes, models, and Python dependencies into a reproducible build. Run it on Comfy Desktop or deploy it to serverless.
Only pay for what you use.
GPU
RTX PRO 6000
96 GB VRAM
$3.49/hr
736.39 credits/hr
H100
80 GB VRAM
$4.79/hr
1010.69 credits/hr
H200
141 GB VRAM
$5.93/hr
1251.23 credits/hr
B200
180 GB VRAM
$8.64/hr
1823.04 credits/hr
Billed by the GPU second
Storage
Network storage
Standard, under 1 TB
$0.091/GB/mo
19.20 credits
Network storage
Standard, 1 TB and above
$0.065/GB/mo
13.72 credits
Network storage
High performance
$0.182/GB/mo
38.40 credits
Container disk
Per-worker local filesystem
$0.13/GB/mo
27.43 credits
Models live on persistent network storage shared across a deployment's workers. Container disk is each worker's local filesystem and is billed separately.
Over every model, every node, every step, every output.
Run ComfyUI on your own hardware.
SEE DESKTOP FEATURESThe full power of ComfyUI from anywhere.
SEE CLOUD FEATURESDeploy and scale ComfyUI workflows.
SEE PLATFORM FEATURESEnterprise-grade infrastructure for the creative engine inside your organization.
SEE ENTERPRISE FEATURES