Vendors · Comparison
Amazon Bedrock Provisioned Throughput vs Vertex AI Provisioned Throughput (now Gemini Enterprise Agent Platform Provisioned Throughput)
Only Bedrock Provisioned Throughput documents HIPAA BAA, 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
Two US hyperscalers, two different capacity units. Amazon Bedrock Provisioned Throughput reserves model units (MUs), billed hourly with no commitment, a 1-month or a 6-month term, and is required to serve a model you have customised on Bedrock. Vertex AI Provisioned Throughput reserves generative AI scale units (GSUs) on fixed-cost terms, including 1-week terms for select models, which suits a short spike such as a launch.
Price visibility differs. AWS pricing includes worked examples with per-model-unit hourly rates, for instance $18.40 per hour per Titan Text Express unit on a 1-month commitment. A public GSU price list is not verified here.
Both make contractual location commitments. Section 1.4 of the AWS Customer Agreement lets you specify the regions where your content is stored. Google’s Service Specific Terms commit to storing data and running machine learning processing in a customer-chosen multi-region. Google LLC is organised under Delaware law per its terms; both parents are US companies, so neither answers the jurisdiction question differently from the other.
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://cloud.google.com/blog/products/ai-machine-learning/provisioned-throughput-on-vertex-ai (checked 2026-10-22)
- https://aws.amazon.com/bedrock/pricing/ (checked 2026-10-22)
- https://aws.amazon.com/agreement/ (checked 2026-10-22)
- https://cloud.google.com/terms/service-terms (checked 2026-10-22)
- https://policies.google.com/terms (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). Vertex AI Provisioned Throughput: Per GSU (generative AI scale unit) fixed-cost term; 1-week terms for select models; orders allow scope changes, term increases and multiple pending changes (publication not verified).
- Category Both are Hyperscaler dedicated offerings.
- Compliance Both document SOC 2 Type II, SOC 3, ISO 27001 and GDPR DPA. Only Amazon Bedrock Provisioned Throughput documents HIPAA BAA, C5 and FedRAMP.
- 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.
Vertex AI Provisioned Throughput (now Gemini Enterprise Agent Platform Provisioned Throughput)
Provisioned Throughput reserves Gemini and partner-model capacity in generative AI scale units (GSUs) on fixed-cost terms, including 1-week options for select models. Google now brands the platform Gemini Enterprise Agent Platform. Its Service Specific Terms commit to storing data and running ML processing in a customer-chosen multi-region. Public GSU price list not verified.
Side by side
Capabilities compared
| Amazon Bedrock Provisioned Throughput | Vertex AI Provisioned Throughput (now Gemini Enterprise Agent Platform Provisioned Throughput) | |
|---|---|---|
| Pricing model | Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms | Per GSU (generative AI scale unit) fixed-cost term; 1-week terms for select models; orders allow scope changes, term increases and multiple pending changes |
| Public pricing | No | Not verified |
| Category | Hyperscaler dedicated | Hyperscaler dedicated |
| Deployment models | Provisioned throughputCustom model (provisioned) | Provisioned throughputSingle-zone provisioned throughput |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | United States, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA | SOC 2 Type IISOC 3ISO 27001GDPR 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 reserves Gemini and partner-model capacity in generative AI scale units (GSUs) on fixed-cost terms, including 1-week options for select models. Google now brands the platform Gemini Enterprise Agent Platform. Its Service Specific Terms commit to storing data and running ML processing in a customer-chosen multi-region. Public GSU price list not verified. |
Where they diverge
Deployment differentiation
Only Amazon Bedrock Provisioned Throughput
Both
Only Vertex AI Provisioned Throughput