Vendors · Comparison
Azure OpenAI Provisioned Throughput (PTU) vs Databricks Model Serving
Side-by-side comparison of Azure OpenAI Provisioned Throughput (PTU) and Databricks Model Serving 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.
Databricks Model Serving
Mosaic AI Model Serving deploys custom MLflow models and fine-tuned foundation models on Databricks-managed serverless compute; provisioned throughput allocates dedicated inference capacity. Trust pages list ISO 27001:2022 (including AWS single-tenant), SOC 2 Type II report on request, HIPAA options, FedRAMP Moderate/High; a standard BAA is published. DPA with SCCs published. Databricks, Inc. is headquartered in San Francisco.
From the data
Key differences
- Category Azure OpenAI Provisioned Throughput (PTU) is a Hyperscaler dedicated offering; Databricks Model Serving is Managed self-host.
- Compliance Both document SOC 2 Type II, ISO 27001, FedRAMP, HIPAA BAA and GDPR DPA. Only Azure OpenAI Provisioned Throughput (PTU) documents C5.
- Data residency Azure OpenAI Provisioned Throughput (PTU) has a verified residency guarantee; Databricks Model Serving'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). Databricks Model Serving: Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs (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) | Databricks Model Serving | |
|---|---|---|
| Category | Hyperscaler dedicated | Managed self-host |
| Deployment models | Global provisionedData-zone provisionedRegional provisioned | Custom model servingProvisioned throughputPay-per-token endpoints |
| Regions | Global, US, Europe | US, Europe, Asia-Pacific |
| Compliance | SOC 2 Type IIISO 27001C5FedRAMPHIPAA BAAGDPR DPA | SOC 2 Type IIISO 27001HIPAA BAAFedRAMPGDPR DPA |
| Pricing model | Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms | Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs |
| 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. | Mosaic AI Model Serving deploys custom MLflow models and fine-tuned foundation models on Databricks-managed serverless compute; provisioned throughput allocates dedicated inference capacity. Trust pages list ISO 27001:2022 (including AWS single-tenant), SOC 2 Type II report on request, HIPAA options, FedRAMP Moderate/High; a standard BAA is published. DPA with SCCs published. Databricks, Inc. is headquartered in San Francisco. |
Where they diverge
Deployment differentiation
Only Azure OpenAI Provisioned Throughput (PTU)
Both
No overlap in deployment models.
Only Databricks Model Serving
Read the full profiles