Vendors · Comparison
Amazon Bedrock Provisioned Throughput vs Scaleway
Side-by-side comparison of Amazon Bedrock Provisioned Throughput and Scaleway 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.
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 Amazon Bedrock Provisioned Throughput is a Hyperscaler dedicated offering; Scaleway is EU sovereign.
- Compliance Both document ISO 27001 and GDPR DPA. Only Amazon Bedrock Provisioned Throughput documents SOC 2 Type II, SOC 3, HIPAA BAA, C5 and FedRAMP.
- Data residency Both have a verified data residency guarantee.
- Jurisdiction Parent jurisdiction: Amazon Bedrock Provisioned Throughput US, Scaleway FR.
- Pricing Amazon Bedrock Provisioned Throughput: Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms (no 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
| Amazon Bedrock Provisioned Throughput | Scaleway | |
|---|---|---|
| Category | Hyperscaler dedicated | EU sovereign |
| Deployment models | Provisioned throughputCustom model (provisioned) | Serverless APIDedicated GPU inference |
| Regions | US, Europe, Asia-Pacific | Europe |
| Compliance | SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA | ISO 27001GDPR DPA |
| Pricing model | Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms | Per-hour dedicated GPU (Managed Inference); per token (Generative APIs) |
| Public pricing | No | Yes |
| Residency guarantee | Yes | Yes |
| Parent jurisdiction | US | FR |
| 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. | 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 Amazon Bedrock Provisioned Throughput
Both
No overlap in deployment models.
Only Scaleway
Read the full profiles