Vendors · Comparison
Modal vs Scaleway Managed Inference (now Generative APIs Dedicated Deployment)
Modal's parent is in the United States; Scaleway's is in the France. Pricing, compliance, regions and residency compared, every fact sourced and dated.
Last verified (older of the two profiles) How we verify
From the data
Key differences
- Pricing Modal: Per-second GPU, CPU core, and memory billing (published pricing). Scaleway: Per-hour dedicated GPU (Generative APIs Dedicated Deployment); per million tokens (Generative APIs serverless) (published pricing).
- Category Both are Dedicated GPU offerings.
- Compliance Only Modal documents SOC 2 Type II. Only Scaleway documents ISO 27001 and GDPR DPA.
- Data residency Both commit to data residency in their contract terms.
- Jurisdiction Parent jurisdiction: Modal United States, Scaleway France.
Generated from the verified vendor data below; sources and dates on each vendor profile.
Modal
Terms commit to processing customer data only in customer-specified regions. HIPAA is offered on the Enterprise plan (Volumes v2 in scope, some features out); no BAA wording was found. Dedicated Endpoints run models on isolated, autoscaling containers at standard compute rates; the pricing page lists no separate dedicated tier.
Scaleway Managed Inference (now Generative APIs Dedicated Deployment)
Generative APIs Dedicated Deployment (formerly 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. Security page lists SecNumCloud as ongoing ("currently undergoing qualification"); not yet qualified. Serverless tier prices cached tokens separately.
Side by side
Capabilities compared
| Modal | Scaleway Managed Inference (now Generative APIs Dedicated Deployment) | |
|---|---|---|
| Pricing model | Per-second GPU, CPU core, and memory billing | Per-hour dedicated GPU (Generative APIs Dedicated Deployment); per million tokens (Generative APIs serverless) |
| Public pricing | Yes | Yes |
| Category | Dedicated GPU | Dedicated GPU |
| Deployment models | ServerlessDedicated endpoints | Serverless APIDedicated GPU inference |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | EU/EEA |
| Compliance | SOC 2 Type II | ISO 27001GDPR DPA |
| Data residency evidence | Contractual | Contractual |
| Parent jurisdiction | United States | France |
| Sovereign for | Not recorded | EU/EEA |
| Analyst note | Terms commit to processing customer data only in customer-specified regions. HIPAA is offered on the Enterprise plan (Volumes v2 in scope, some features out); no BAA wording was found. Dedicated Endpoints run models on isolated, autoscaling containers at standard compute rates; the pricing page lists no separate dedicated tier. | Generative APIs Dedicated Deployment (formerly 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. Security page lists SecNumCloud as ongoing ("currently undergoing qualification"); not yet qualified. Serverless tier prices cached tokens separately. |
Where they diverge
Deployment differentiation
Only Modal
Both
No overlap in deployment models.
Only Scaleway
Read the full profiles