Serverless GPU
Serverless GPU covers services that run code on a GPU and bill by the second, with no server to manage.
In brief
Serverless GPU, in brief.
What it isServerless GPU covers services that run code on a GPU and bill by the second, with no server to manage.
Where it sitsOne of 14 categories in the Compute layer. Compute is the hardware AI runs on and the companies that rent it out: GPU clouds, AI chips, servers, data centres, and the software that schedules jobs across them. It is where the cost of training and running models is set.
What we track20 products, including Amazon SageMaker Serverless/Async Inference, Azure Container Apps serverless GPUs, Baseten, Beam and Cerebrium.
The products
20 products in Serverless GPU.
Each name opens a search for that product in our index.
ProductMakerIts own site
From our census of 2026-11-08. A product listed here is one that belongs in this category; the search answer says whether we have checked it.
Questions
Serverless GPU, answered.
What is Serverless GPU in AI infrastructure?Serverless GPU covers services that run code on a GPU and bill by the second, with no server to manage.
Which layer of AI infrastructure is Serverless GPU in?Serverless GPU is in the Compute layer. Compute is the hardware AI runs on and the companies that rent it out: GPU clouds, AI chips, servers, data centres, and the software that schedules jobs across them. It is where the cost of training and running models is set.
Which products are in Serverless GPU?We track 20 products in Serverless GPU, including Amazon SageMaker Serverless/Async Inference, Azure Container Apps serverless GPUs, Baseten, Beam, Cerebrium, Cloudflare Workers AI, DeepInfra (custom model deployments) and fal. The full list is on this page.
Compute
The other categories in Compute.
AI chips / accelerator cloudsAI data centres & colocationAI networking & optical interconnectAI servers & on-prem systemsAI storage for GPU clustersCloud GPU notebooks & dev environmentsCompute price indexes & GPU price trackersEdge AI accelerators & NPU toolchainsGPU cluster schedulers & orchestrationGPU marketplacesGPU observability & efficiencyHyperscaler GPUNeoclouds / GPU clouds