Vendors · Comparison
Azure OpenAI Provisioned Throughput (PTU) vs Modal
Only Azure OpenAI PTU documents ISO 27001, C5 and FedRAMP. Pricing, compliance, regions and residency compared, every fact sourced and dated.
Last verified (older of the two profiles) How we verify
Analysis
What separates them
These answer different questions. Azure OpenAI Provisioned Throughput reserves capacity for Microsoft-hosted OpenAI models. Modal runs your own models and code on GPUs it manages.
That shows up in billing. Azure sells provisioned throughput units, billed hourly or through 1-month or 1-year Azure Reservations, with per-PTU minimums: on 22 October 2026, GPT-5.5 needed at least 15 PTUs on a Global deployment at $1 per PTU per hour (Microsoft labels these estimates). Modal bills per second for GPU, CPU and memory.
Both make contractual location commitments. Modal’s terms let the customer restrict processing of customer data to the regions it specifies, and Modal will not process it elsewhere without consent. Azure’s deployment types keep processing within a US, EU or Asia Pacific data zone, or within one Azure geography for Regional deployments.
Both parents are US companies (Modal Labs, Inc. is a Delaware corporation per its terms), so jurisdiction is not the deciding factor here; the choice is between reserved access to one model family and per-second compute for any model.
Last verified (every source below) How we verify
Sources (5)
- https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing (checked 2026-10-22)
- https://azure.microsoft.com/en-us/pricing/details/azure-openai/ (checked 2026-10-22)
- https://modal.com/pricing (checked 2026-10-22)
- https://modal.com/legal/terms (checked 2026-10-22)
- https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types (checked 2026-10-22)
From the data
Key differences
- Pricing Azure OpenAI Provisioned Throughput (PTU): Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms (published pricing). Modal: Per-second GPU, CPU core, and memory billing (published pricing).
- Category Azure OpenAI Provisioned Throughput (PTU) is a Hyperscaler dedicated offering; Modal is Dedicated GPU.
- Compliance Both document SOC 2 Type II. Only Azure OpenAI Provisioned Throughput (PTU) documents ISO 27001, C5, FedRAMP, HIPAA BAA and GDPR DPA.
- Data residency Both commit to data residency in their contract terms.
- Jurisdiction Both parent companies are under United States jurisdiction.
Generated from the verified vendor data below; sources and dates on each vendor profile.
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 or APAC), 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.
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.
Side by side
Capabilities compared
| Azure OpenAI Provisioned Throughput (PTU) | Modal | |
|---|---|---|
| Pricing model | Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms | Per-second GPU, CPU core, and memory billing |
| Public pricing | Yes | Yes |
| Category | Hyperscaler dedicated | Dedicated GPU |
| Deployment models | Global provisionedData-zone provisionedRegional provisioned | ServerlessDedicated endpoints |
| Regions | Global, United States, EU/EEA, Asia-Pacific | United States, United Kingdom, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type IIISO 27001C5FedRAMPHIPAA BAAGDPR DPA | SOC 2 Type II |
| Data residency evidence | Contractual | Contractual |
| Parent jurisdiction | United States | United States |
| Sovereign for | Not recorded | Not recorded |
| 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 or APAC), 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. | 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. |
Where they diverge
Deployment differentiation
Only Azure OpenAI Provisioned Throughput (PTU)
Both
No overlap in deployment models.
Only Modal
Read the full profiles