Cassava AI

Check the cited vendor page before you rent from Cassava AI.

Offers NVIDIA H200 GPU-as-a-Service with isolated MIG instances and on-demand hourly, reserved and interruptible spot capacity for AI workloads.

Address: Online, Global, United Kingdom
Website: www.cassava.ai/
GPU models: H200
Billing: per hour
Spot capacity: Yes
Source note: Facts from the vendor's own website (https://www.cassava.ai/ai-compute/gpu-as-a-service/), fetched 2026-10-29.

Photos

Cassava AI is at Online, Global, United Kingdom.

To contact Cassava AI, visit https://www.cassava.ai/.

GPU neocloudsOnline
Civo
Cloud provider offering NVIDIA GPUs (B200, H200, H100, A100, L40S) on its compute and Kubernetes services with hourly on-demand or committed pricing, plus…
Lowest on-demand H100 rate
299 US cents/GPU-h
Lowest on-demand A100 rate
109 US cents/GPU-h
GPU neocloudsOnline
Hyperstack
GPU cloud by NexGen Cloud offering on-demand, reserved and spot NVIDIA GPU VMs (B300, B200, H200, H100, A100, L40, RTX Pro 6000) billed per minute, plus…
Lowest on-demand H100 rate
250 US cents/GPU-h
Lowest on-demand A100 rate
135 US cents/GPU-h
Serverless GPUOnline
Northflank
Container deployment platform running workloads on Kubernetes in Northflank Cloud or the customer's own cloud, with on-demand NVIDIA GPUs (L4, A100, H100,…
Lowest on-demand H100 rate
274 US cents/GPU-h
Lowest on-demand A100 rate
142 US cents/GPU-h
GPU neocloudsOnline
Radiant (formerly Ori)
AI cloud formed from the merger of Ori Industries and Brookfield AI infrastructure; Ori's GPU cloud continues as Radiant AI Cloud with GPU VMs, bare metal,…
Inference platformsOnline
Runware
AI cloud offering model APIs, autoscaling serverless GPU workloads and reserved bare-metal clusters on its modular Sonic Pod infrastructure, with GPU usage…
Lowest on-demand H100 rate
395 US cents/GPU-h
Bare-metal GPU clustersOnline
CUDO Compute
Dedicated NVIDIA GPU clusters and managed AI infrastructure for training and inference, with deployment, networking, storage and operational support across…