Vendors · Comparison
Amazon Bedrock Provisioned Throughput vs Azure OpenAI Provisioned Throughput (PTU)
Azure OpenAI PTU publishes its prices; Bedrock Provisioned Throughput has no full public price list. Pricing, compliance and residency compared, with sources.
Last verified (older of the two profiles) How we verify
Analysis
What separates them
Both are US hyperscalers selling reserved model capacity, so the difference is in the unit, the term and the price you can see before talking to sales.
Amazon Bedrock Provisioned Throughput is sold in model units (MUs), billed hourly with no commitment, a 1-month or a 6-month term; longer terms lower the hourly rate. If you customise a model on Bedrock, provisioned throughput is the only way to serve it. AWS pricing shows worked examples, such as two Titan Text Express model units on a 1-month commitment at $18.40 per hour each.
Azure OpenAI Provisioned Throughput is sold in PTUs, billed hourly or through Azure Reservations on 1-month or 1-year terms. Microsoft publishes a per-PTU table by model and deployment type; on 22 October 2026 GPT-5.5 listed at $1 per PTU per hour on Global, $1.10 on Data Zone and $2 on Regional deployments, labelled as estimates.
On location, the AWS Customer Agreement (section 1.4) lets you specify the AWS regions where your content is stored. Azure’s deployment types set where prompts are processed: globally, within a US, EU or Asia Pacific data zone, or within one Azure geography.
Last verified (every source below) How we verify
Sources (6)
- https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html (checked 2026-10-22)
- https://aws.amazon.com/bedrock/pricing/ (checked 2026-10-22)
- 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://aws.amazon.com/agreement/ (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 Amazon Bedrock Provisioned Throughput: Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms (no published pricing). Azure OpenAI Provisioned Throughput (PTU): Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms (published pricing).
- Category Both are Hyperscaler dedicated offerings.
- Compliance Both document SOC 2 Type II, ISO 27001, HIPAA BAA, C5, FedRAMP and GDPR DPA. Only Amazon Bedrock Provisioned Throughput documents SOC 3.
- 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.
Amazon Bedrock Provisioned Throughput
Provisioned Throughput reserves per-model capacity in Model Units (MUs), billed hourly with no-commitment, 1-month, or 6-month terms; required for serving customised models. AWS states Bedrock content is stored at rest in the Region of use and not shared with model providers. Example per-MU rates are published for some models; most quotes require an AWS account team.
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.
Side by side
Capabilities compared
| Amazon Bedrock Provisioned Throughput | Azure OpenAI Provisioned Throughput (PTU) | |
|---|---|---|
| Pricing model | Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms | Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms |
| Public pricing | No | Yes |
| Category | Hyperscaler dedicated | Hyperscaler dedicated |
| Deployment models | Provisioned throughputCustom model (provisioned) | Global provisionedData-zone provisionedRegional provisioned |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | Global, United States, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA | SOC 2 Type IIISO 27001C5FedRAMPHIPAA BAAGDPR DPA |
| Data residency evidence | Contractual | Contractual |
| Parent jurisdiction | United States | United States |
| Sovereign for | Not recorded | Not recorded |
| Analyst note | Provisioned Throughput reserves per-model capacity in Model Units (MUs), billed hourly with no-commitment, 1-month, or 6-month terms; required for serving customised models. AWS states Bedrock content is stored at rest in the Region of use and not shared with model providers. Example per-MU rates are published for some models; most quotes require an AWS account team. | 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. |
Where they diverge
Deployment differentiation
Only Amazon Bedrock Provisioned Throughput
Both
No overlap in deployment models.
Only Azure OpenAI Provisioned Throughput (PTU)