Vendors · Comparison
Azure OpenAI Provisioned Throughput (PTU) vs Baseten
Side-by-side comparison of Azure OpenAI Provisioned Throughput (PTU) and Baseten 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.
Baseten
Dedicated deployments and an enterprise self-hosted option position Baseten for single-tenant use. No public data-residency guarantee found at review; trust centre lists subprocessors across multiple clouds.
From the data
Key differences
- Category Azure OpenAI Provisioned Throughput (PTU) is a Hyperscaler dedicated offering; Baseten is Dedicated GPU.
- Compliance Both document SOC 2 Type II, HIPAA BAA and GDPR DPA. Only Azure OpenAI Provisioned Throughput (PTU) documents ISO 27001, C5 and FedRAMP. Only Baseten documents SOC 3.
- Data residency Azure OpenAI Provisioned Throughput (PTU) has a verified residency guarantee; Baseten's residency guarantee is not verified.
- Jurisdiction Both parent companies are under US jurisdiction.
- Pricing Azure OpenAI Provisioned Throughput (PTU): Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms (published pricing). Baseten: Per 1M tokens (Model APIs); per-minute GPU/CPU instances for dedicated deployments (published pricing).
Generated from the verified vendor data below; sources and dates on each vendor profile.
Side by side
Capabilities compared
| Azure OpenAI Provisioned Throughput (PTU) | Baseten | |
|---|---|---|
| Category | Hyperscaler dedicated | Dedicated GPU |
| Deployment models | Global provisionedData-zone provisionedRegional provisioned | Dedicated deploymentSelf-hostedHybrid |
| Regions | Global, US, Europe | US, UK, Europe, Asia-Pacific |
| Compliance | SOC 2 Type IIISO 27001C5FedRAMPHIPAA BAAGDPR DPA | SOC 2 Type IISOC 3HIPAA BAAGDPR DPA |
| Pricing model | Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms | Per 1M tokens (Model APIs); per-minute GPU/CPU instances for dedicated deployments |
| Public pricing | Yes | Yes |
| Residency guarantee | Yes | Not verified |
| Parent jurisdiction | US | US |
| 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. | Dedicated deployments and an enterprise self-hosted option position Baseten for single-tenant use. No public data-residency guarantee found at review; trust centre lists subprocessors across multiple clouds. |
Where they diverge
Deployment differentiation
Only Azure OpenAI Provisioned Throughput (PTU)
Both
No overlap in deployment models.
Only Baseten
Read the full profiles