Vendors · Comparison
Together AI vs Vertex AI Provisioned Throughput
Side-by-side comparison of Together AI and Vertex AI Provisioned Throughput for single-tenant LLM hosting. Deployment options, compliance, pricing, and operational fit compared.
Together AI
Dedicated endpoints are explicitly single-tenant GPU instances with public per-hour pricing. Terms of service make no geographic storage commitment, so residency guarantee is recorded as none.
Vertex AI 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 Cloud docs now brand the platform Gemini Enterprise Agent Platform. Vertex AI Platform appears in Google's SOC 1/2/3 and ISO 27001 scope; public GSU price list not verified at review.
From the data
Key differences
- Category Together AI is a Dedicated GPU offering; Vertex AI Provisioned Throughput is Hyperscaler dedicated.
- Compliance Both document SOC 2 Type II. Only Together AI documents HIPAA BAA. Only Vertex AI Provisioned Throughput documents SOC 3, ISO 27001 and GDPR DPA.
- Data residency Together AI offers no residency guarantee (verified); Vertex AI Provisioned Throughput's residency guarantee is not verified.
- Jurisdiction Both parent companies are under US jurisdiction.
- Pricing Together AI: Per 1M tokens serverless; per GPU-hour for dedicated endpoints and clusters (published pricing). Vertex AI Provisioned Throughput: Per GSU (generative AI scale unit) fixed-cost term; 1-week terms for select models (publication not verified).
Generated from the verified vendor data below; sources and dates on each vendor profile.
Side by side
Capabilities compared
| Together AI | Vertex AI Provisioned Throughput | |
|---|---|---|
| Category | Dedicated GPU | Hyperscaler dedicated |
| Deployment models | ServerlessDedicated endpointGPU clusters | Provisioned throughputSingle-zone provisioned throughput |
| Regions | Not verified | US, Europe, Asia-Pacific |
| Compliance | SOC 2 Type IIHIPAA BAA | SOC 2 Type IISOC 3ISO 27001GDPR DPA |
| Pricing model | Per 1M tokens serverless; per GPU-hour for dedicated endpoints and clusters | Per GSU (generative AI scale unit) fixed-cost term; 1-week terms for select models |
| Public pricing | Yes | Not verified |
| Residency guarantee | No | Not verified |
| Parent jurisdiction | US | US |
| Analyst note | Dedicated endpoints are explicitly single-tenant GPU instances with public per-hour pricing. Terms of service make no geographic storage commitment, so residency guarantee is recorded as none. | 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 Cloud docs now brand the platform Gemini Enterprise Agent Platform. Vertex AI Platform appears in Google's SOC 1/2/3 and ISO 27001 scope; public GSU price list not verified at review. |
Where they diverge
Deployment differentiation
Only Together AI
Both
No overlap in deployment models.
Only Vertex AI Provisioned Throughput
Read the full profiles