cassava.ai resells H200 GPU capacity through AI Compute, GPU as a Service, bare-metal infrastructure and managed AI services. Its listed delivery location is Johannesburg with SOC 2 and HIPAA controls for enterprise and sovereign AI workloads.
cassava.ai sources GPU capacity from Site mentions GCP infrastructure and resells it with a managed layer on top. This model can simplify the buying process for teams that prefer not to deal with the underlying provider directly.
There is a margin built in and transparency over where the hardware runs is limited. Compare against the underlying provider before committing at scale.
Best for: Teams that value managed sourcing over dealing with the underlying operator directly. Not for: Buyers who require direct-to-metal accountability from the infrastructure owner.
Confidence: MediumEvidence reviewed: 3 checks
Indicator
Reseller classification
cassava.ai sources capacity from Site mentions GCP infrastructure and resells access with a managed layer.
Indicator
Provenance
Infrastructure is not independently operated. Buyers requiring direct-operator guarantees should compare against the source provider.
REVIEWS
Buyer reviews
Moderated buyer feedback. Independent from the viabandwidth assessment above.
Had a good or bad experience with cassava.ai?
Be the first to review cassava.ai. Moderated and kept separate from viabandwidth’s own assessment.
Is cassava.ai a direct GPU operator or a reseller?
cassava.ai is classified as a reseller. Teams that value managed sourcing over dealing with the underlying operator directly. Buyers who require direct-to-metal accountability from the infrastructure owner.
What GPU models does cassava.ai offer?
cassava.ai lists H200 across its published capacity.
How much does cassava.ai charge for GPU compute?
cassava.ai does not publish list pricing. Visit their site or use the contact form on this page for a quote.
Is cassava.ai's viabandwidth listing verified?
Not yet. This profile is compiled by viabandwidth from public sources. cassava.ai has not claimed it.
OVERVIEW
Company overview
Operator class
Reseller
GPU models tracked
H200
Services
GPU compute, Managed services, Bare metal
CAPACITY
GPU lineup by use case
Tracked GPU SKUs grouped by the workload they fit best.
Training
For multi-node runs where interconnect and cluster availability decide the outcome.
H200
QuoteClaim to publish
VRAM 141 GBClass Hopper
Best for Large-scale training where memory bandwidth decides the outcome.
COMMERCIALS
Pricing
Indicative published rates. Final cluster pricing depends on commit length, storage, networking and capacity.
Pricing on request. Visit cassava.ai’s site for a quote.
COMPARE
Similar GPU providers
Other reseller operators buyers compare cassava.ai against.
Profile pages, buyer guides and model explainers stay open. Vendor packages cover what shows on this profile. Verification stays independent and is never for sale.