Vendors · Comparison
Hugging Face Inference Endpoints vs Vertex AI Provisioned Throughput (now Gemini Enterprise Agent Platform Provisioned Throughput)
Only Vertex AI Provisioned Throughput documents SOC 3 and ISO 27001. Pricing, compliance, regions and residency compared, every fact sourced and dated.
Last verified (older of the two profiles) How we verify
From the data
Key differences
- Pricing Hugging Face Inference Endpoints: Per instance-hour (CPU, GPU, and accelerator instances); dedicated inference from $0.033/hour (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 Hugging Face Inference Endpoints is a Managed self-host offering; Vertex AI Provisioned Throughput is Hyperscaler dedicated.
- Compliance Both document SOC 2 Type II and GDPR DPA. Only Vertex AI Provisioned Throughput documents SOC 3 and ISO 27001.
- Data residency Hugging Face Inference Endpoints's data residency is not verified; Vertex AI Provisioned Throughput commits to data residency in its 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.
Hugging Face Inference Endpoints
Deploys Hub models on managed instances across AWS, Azure, and GCP with public, protected, or private (intra-region AWS/Azure PrivateLink) access. Vendor docs state SOC 2 Type 2 certification and a GDPR DPA via Enterprise Hub subscription, and that payloads are not stored (logs kept 30 days). Privacy policy: data may be stored in the US.
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
| Hugging Face Inference Endpoints | Vertex AI Provisioned Throughput (now Gemini Enterprise Agent Platform Provisioned Throughput) | |
|---|---|---|
| Pricing model | Per instance-hour (CPU, GPU, and accelerator instances); dedicated inference from $0.033/hour | 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 | Yes | Not verified |
| Category | Managed self-host | Hyperscaler dedicated |
| Deployment models | Dedicated endpointsPublic endpointProtected endpointPrivate endpoint (PrivateLink) | Provisioned throughputSingle-zone provisioned throughput |
| Regions | United States, EU/EEA | United States, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type II (stated)GDPR DPA (stated) | SOC 2 Type IISOC 3ISO 27001GDPR DPA |
| Data residency evidence | Not verified | Contractual |
| Parent jurisdiction | United States | United States |
| Sovereign for | Not recorded | Not recorded |
| Analyst note | Deploys Hub models on managed instances across AWS, Azure, and GCP with public, protected, or private (intra-region AWS/Azure PrivateLink) access. Vendor docs state SOC 2 Type 2 certification and a GDPR DPA via Enterprise Hub subscription, and that payloads are not stored (logs kept 30 days). Privacy policy: data may be stored in the US. | 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 Hugging Face Inference Endpoints
Both
No overlap in deployment models.
Only Vertex AI Provisioned Throughput