Vendors · Comparison
Azure OpenAI Provisioned Throughput (PTU) vs Nebius
Side-by-side comparison of Azure OpenAI Provisioned Throughput (PTU) and Nebius for single-tenant LLM hosting. Deployment options, compliance, pricing, and operational fit compared.
Azure OpenAI Provisioned Throughput (PTU)
Provisioned throughput is now a Microsoft Foundry (formerly Azure AI Foundry) deployment type billed hourly per PTU, with 1-month or 1-year Azure Reservations. Global, Data Zone (US/EU), and Regional options set where prompts are processed; stored data stays in the customer-designated geography. FedRAMP scope names Azure OpenAI; SOC 2, ISO 27001, and C5 attest the Azure platform.
Nebius
Token Factory offers shared or single-tenant endpoints with optional regional deployment in EU or US data centers (Finland, France, US). Contracting entity Nebius B.V. is a Dutch company governed by Netherlands law. Trust center lists HIPAA alongside SOC 2 Type II; no explicit BAA statement found at review. Per-token price list requires account sign-in.
From the data
Key differences
- Category Azure OpenAI Provisioned Throughput (PTU) is a Hyperscaler dedicated offering; Nebius is EU sovereign.
- Compliance Both document SOC 2 Type II, ISO 27001 and GDPR DPA. Only Azure OpenAI Provisioned Throughput (PTU) documents C5, FedRAMP and HIPAA BAA. Only Nebius documents SOC 3.
- Data residency Azure OpenAI Provisioned Throughput (PTU) has a verified residency guarantee; Nebius's residency guarantee is not verified.
- Jurisdiction Parent jurisdiction: Azure OpenAI Provisioned Throughput (PTU) US, Nebius NL.
- Pricing Azure OpenAI Provisioned Throughput (PTU): Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms (published pricing). Nebius: Per 1M input/output tokens; shared and dedicated endpoint tiers (publication not verified).
Generated from the verified vendor data below; sources and dates on each vendor profile.
Side by side
Capabilities compared
| Azure OpenAI Provisioned Throughput (PTU) | Nebius | |
|---|---|---|
| Category | Hyperscaler dedicated | EU sovereign |
| Deployment models | Global provisionedData-zone provisionedRegional provisioned | Serverless APIDedicated endpoints |
| Regions | Global, US, Europe | Europe, US |
| Compliance | SOC 2 Type IIISO 27001C5FedRAMPHIPAA BAAGDPR DPA | SOC 2 Type IISOC 3ISO 27001GDPR DPA |
| Pricing model | Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms | Per 1M input/output tokens; shared and dedicated endpoint tiers |
| Public pricing | Yes | Not verified |
| Residency guarantee | Yes | Not verified |
| Parent jurisdiction | US | NL |
| Analyst note | Provisioned throughput is now a Microsoft Foundry (formerly Azure AI Foundry) deployment type billed hourly per PTU, with 1-month or 1-year Azure Reservations. Global, Data Zone (US/EU), and Regional options set where prompts are processed; stored data stays in the customer-designated geography. FedRAMP scope names Azure OpenAI; SOC 2, ISO 27001, and C5 attest the Azure platform. | Token Factory offers shared or single-tenant endpoints with optional regional deployment in EU or US data centers (Finland, France, US). Contracting entity Nebius B.V. is a Dutch company governed by Netherlands law. Trust center lists HIPAA alongside SOC 2 Type II; no explicit BAA statement found at review. Per-token price list requires account sign-in. |
Where they diverge
Deployment differentiation
Only Azure OpenAI Provisioned Throughput (PTU)
Both
No overlap in deployment models.
Only Nebius
Read the full profiles