Serverless GPU

Filter thousands of providers instantly. Everything happens in your browser.

17 providers
RunPod2022Developer GPU cloud with per-second Pods, serverless endpoints and community hosts$0.240/GPU-hr
Modal2021Python-native serverless cloud with per-second GPUs from T4 to B300$1.95/GPU-hr
fal2021Generative media platform with pay-per-use model APIs and serverless GPUs$4.00/GPU-hr
Cerebrium2021Real-time serverless GPU platform for voice, LLM and video inference$1.95/GPU-hr
FriendliAI2021Inference platform with model APIs, per-second dedicated GPUs and bring-your-own-GPU$4.00/GPU-hr
Hugging Face2016AI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference$0.800/GPU-hr
DeepInfra2013Low-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute$0.890/GPU-hr
Fireworks AI2022Fast inference and fine-tuning platform with per-second on-demand GPU deployments$8.00/GPU-hr
Baseten2019Inference platform for dedicated model deployments and model APIs, billed per minute$0.848/GPU-hr
Beam2019Serverless GPUs, sandboxes and BYOC deployments billed by the millisecond$0.691/GPU-hr
Salad1999SaladCloud runs containers on a distributed network of consumer RTX GPUs$0.330/GPU-hr
Novita AI2023Model APIs plus on-demand, spot and serverless GPU instances and bare metal—
Chutes2024Open-source, decentralized serverless platform for running open models at scale—
Replicate2019Run and deploy open models through an API, billed per second; now part of Cloudflare$0.810/GPU-hr
Lepton AI2023AI cloud platform acquired by NVIDIA and relaunched as DGX Cloud Lepton—
Inferless2022Serverless GPU inference startup whose team joined Baseten in 2026—
Banana2021Serverless GPU inference platform shut down in March 2024—
Loading index…