singletenant.ai

Vendors · Comparison

Azure OpenAI Provisioned Throughput (PTU) vs Together AI

Only Azure OpenAI PTU documents C5, FedRAMP and GDPR DPA. 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

Both vendors sell something they call a PTU, and the units are not the same. On Azure OpenAI Provisioned Throughput, a provisioned throughput unit reserves capacity on Microsoft-hosted OpenAI models, billed hourly or through 1-month or 1-year reservations. On Together AI, reserved dedicated capacity is sold in throughput units whose tokens per minute depend on the model, on top of per-GPU-hour dedicated endpoints for open models.

Prices are public on both. Microsoft’s table listed GPT-5.5 at $1 per PTU per hour on a Global deployment on 22 October 2026, with a 15-PTU minimum (labelled estimates). Together lists dedicated endpoint prices per GPU per hour.

Isolation and residency differ in strength. Together says every dedicated deployment runs on single-tenant, isolated GPUs and that customers choose the deployment region for data residency, but its terms make no geographic commitment, so residency is Stated. Azure’s deployment types bind processing to a data zone or geography, and this site records Azure residency as Contractual (see the profile).

Both are US companies; Together Computer, Inc. is a Delaware corporation.

Last verified (every source below) How we verify

Sources (6)

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). Together AI: Per 1M tokens serverless; per GPU-hour for dedicated endpoints and clusters (published pricing).
  • Category Azure OpenAI Provisioned Throughput (PTU) is a Hyperscaler dedicated offering; Together AI is Dedicated GPU.
  • Compliance Both document SOC 2 Type II, ISO 27001 and HIPAA BAA. Only Azure OpenAI Provisioned Throughput (PTU) documents C5, FedRAMP and GDPR DPA.
  • Data residency Azure OpenAI Provisioned Throughput (PTU) commits to data residency in its contract terms; Together AI states data residency on its own pages (not contractual).
  • 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.

Together AI

Dedicated endpoints are explicitly single-tenant GPU instances with public per-hour pricing. The dedicated endpoints page says customers choose the deployment region for data residency; the terms make no geographic commitment, so residency is Stated. ISO 27001:2022 certified by A-LIGN, an ANAB-accredited body. Reserved dedicated capacity is also sold in throughput units (PTUs).

Side by side

Capabilities compared

Azure OpenAI Provisioned Throughput (PTU) Together AI
Pricing model Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms Per 1M tokens serverless; per GPU-hour for dedicated endpoints and clusters
Public pricing Yes Yes
Category Hyperscaler dedicated Dedicated GPU
Deployment models Global provisionedData-zone provisionedRegional provisioned ServerlessDedicated endpointGPU clusters
Regions Global, United States, EU/EEA, Asia-Pacific Not verified
Compliance SOC 2 Type IIISO 27001C5FedRAMPHIPAA BAAGDPR DPA SOC 2 Type II (stated)HIPAA BAA (stated)ISO 27001
Data residency evidence Contractual Stated
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. Dedicated endpoints are explicitly single-tenant GPU instances with public per-hour pricing. The dedicated endpoints page says customers choose the deployment region for data residency; the terms make no geographic commitment, so residency is Stated. ISO 27001:2022 certified by A-LIGN, an ANAB-accredited body. Reserved dedicated capacity is also sold in throughput units (PTUs).

Where they diverge

Deployment differentiation

Only Azure OpenAI Provisioned Throughput (PTU)

Global provisionedData-zone provisionedRegional provisioned

Both

No overlap in deployment models.

Only Together AI

ServerlessDedicated endpointGPU clusters