Vendors · Comparison
CoreWeave vs Scaleway
Side-by-side comparison of CoreWeave and Scaleway for single-tenant LLM hosting. Deployment options, compliance, pricing, and operational fit compared.
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.
Scaleway
Managed Inference runs models on dedicated GPUs at fixed hourly rates (e.g. Llama 3.1-8b at 0.93 EUR/hour) inside a VPC; prompts and responses are stated as stored only in Europe. Scaleway SAS is registered in Paris, France (legal notice). Security page says the SecNumCloud qualification process was entered in January 2025; not yet listed as qualified.
From the data
Key differences
- Category CoreWeave is a Dedicated GPU offering; Scaleway is EU sovereign.
- Compliance Both document GDPR DPA. Only CoreWeave documents SOC 2 Type II. Only Scaleway documents ISO 27001.
- Data residency CoreWeave's residency guarantee is not verified; Scaleway has a verified residency guarantee.
- Jurisdiction Parent jurisdiction: CoreWeave US, Scaleway FR.
- Pricing CoreWeave: Per-GPU-hour on-demand and spot; reserved capacity at up to 60% discount (published pricing). Scaleway: Per-hour dedicated GPU (Managed Inference); per token (Generative APIs) (published pricing).
Generated from the verified vendor data below; sources and dates on each vendor profile.
Side by side
Capabilities compared
| CoreWeave | Scaleway | |
|---|---|---|
| Category | Dedicated GPU | EU sovereign |
| Deployment models | Bare metalManaged KubernetesOn-demandSpotReserved capacity | Serverless APIDedicated GPU inference |
| Regions | US, UK, Europe | Europe |
| Compliance | SOC 2 Type IIGDPR DPA | ISO 27001GDPR DPA |
| Pricing model | Per-GPU-hour on-demand and spot; reserved capacity at up to 60% discount | Per-hour dedicated GPU (Managed Inference); per token (Generative APIs) |
| Public pricing | Yes | Yes |
| Residency guarantee | Not verified | Yes |
| Parent jurisdiction | US | FR |
| Analyst note | 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. | Managed Inference runs models on dedicated GPUs at fixed hourly rates (e.g. Llama 3.1-8b at 0.93 EUR/hour) inside a VPC; prompts and responses are stated as stored only in Europe. Scaleway SAS is registered in Paris, France (legal notice). Security page says the SecNumCloud qualification process was entered in January 2025; not yet listed as qualified. |
Where they diverge
Deployment differentiation
Only CoreWeave
Both
No overlap in deployment models.
Only Scaleway
Read the full profiles