singletenant.ai

Vendors · Comparison

Amazon Bedrock Provisioned Throughput vs CoreWeave

Side-by-side comparison of Amazon Bedrock Provisioned Throughput and CoreWeave for single-tenant LLM hosting. Deployment options, compliance, pricing, and operational fit compared.

Amazon Bedrock Provisioned Throughput

Provisioned Throughput reserves per-model capacity in Model Units (MUs), billed hourly with no-commitment, 1-month, or 6-month terms; required for serving customised models. AWS states Bedrock content is stored at rest in the Region of use and not shared with model providers. Example per-MU rates are published for some models; most quotes require an AWS account team.

CoreWeave

Security page states every CKS node is single-tenant; CKS runs Kubernetes directly on bare-metal nodes without a hypervisor. SOC 2 Type II scope covers Bare Metal and CKS. Trust centre shows ISO 27001/27017/27018 badges but the security page uses "aligned with" wording, so ISO 27001 is excluded (https://www.coreweave.com/security). Terms name CoreWeave, Inc. under New York law.

From the data

Key differences

  • Category Amazon Bedrock Provisioned Throughput is a Hyperscaler dedicated offering; CoreWeave is Dedicated GPU.
  • Compliance Both document SOC 2 Type II and GDPR DPA. Only Amazon Bedrock Provisioned Throughput documents SOC 3, ISO 27001, HIPAA BAA, C5 and FedRAMP.
  • Data residency Amazon Bedrock Provisioned Throughput has a verified residency guarantee; CoreWeave's residency guarantee is not verified.
  • Jurisdiction Both parent companies are under US jurisdiction.
  • Pricing Amazon Bedrock Provisioned Throughput: Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms (no published pricing). CoreWeave: Per-GPU-hour on-demand and spot; reserved capacity at up to 60% discount (published pricing).

Generated from the verified vendor data below; sources and dates on each vendor profile.

Side by side

Capabilities compared

Amazon Bedrock Provisioned Throughput CoreWeave
Category Hyperscaler dedicated Dedicated GPU
Deployment models Provisioned throughputCustom model (provisioned) Bare metalManaged KubernetesOn-demandSpotReserved capacity
Regions US, Europe, Asia-Pacific US, UK, Europe
Compliance SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA SOC 2 Type IIGDPR DPA
Pricing model Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms Per-GPU-hour on-demand and spot; reserved capacity at up to 60% discount
Public pricing No Yes
Residency guarantee Yes Not verified
Parent jurisdiction US US
Analyst note Provisioned Throughput reserves per-model capacity in Model Units (MUs), billed hourly with no-commitment, 1-month, or 6-month terms; required for serving customised models. AWS states Bedrock content is stored at rest in the Region of use and not shared with model providers. Example per-MU rates are published for some models; most quotes require an AWS account team. Security page states every CKS node is single-tenant; CKS runs Kubernetes directly on bare-metal nodes without a hypervisor. SOC 2 Type II scope covers Bare Metal and CKS. Trust centre shows ISO 27001/27017/27018 badges but the security page uses "aligned with" wording, so ISO 27001 is excluded (https://www.coreweave.com/security). Terms name CoreWeave, Inc. under New York law.

Where they diverge

Deployment differentiation

Only Amazon Bedrock Provisioned Throughput

Provisioned throughputCustom model (provisioned)

Both

No overlap in deployment models.

Only CoreWeave

Bare metalManaged KubernetesOn-demandSpotReserved capacity

Read the full profiles