Vendors
16 providers of dedicated or single-tenant LLM hosting, ordered alphabetically. Click a vendor for the full evidence-linked profile.
| Vendor | Category | Deployment | Regions | Compliance | Pricing | Data residency |
|---|---|---|---|---|---|---|
| Amazon Bedrock Provisioned Throughput | Hyperscaler dedicated | Provisioned throughput, Custom model (provisioned) | United States, United Kingdom, EU/EEA, Asia-Pacific | SOC 2 Type II, SOC 3, ISO 27001, HIPAA BAA, C5, FedRAMP, GDPR DPA | Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms | Contractual (United States parent) |
| Azure OpenAI Provisioned Throughput (PTU) | Hyperscaler dedicated | Global provisioned, Data-zone provisioned, Regional provisioned | Global, United States, EU/EEA, Asia-Pacific | SOC 2 Type II, ISO 27001, C5, FedRAMP, HIPAA BAA, GDPR DPA | Per PTU per hour; Azure Reservations discount with 1-month or 1-year terms | Contractual (United States parent) |
| Baseten | Dedicated GPU | Dedicated deployment, Self-hosted, Hybrid | United States, EU/EEA | SOC 2 Type II, SOC 3, ISO 27001, HIPAA BAA, GDPR DPA | Per 1M tokens (Model APIs); per-minute GPU/CPU instances for dedicated deployments | Stated (United States parent) |
| Civo | Dedicated GPU | Bare metal, Managed Kubernetes, Dedicated GPU inference | United Kingdom | ISO 27001 (stated) , SOC 2 Type II (stated) | Per-GPU-hour on demand, lower rates on 6-36 month commitments | Stated (United Kingdom parent) Sovereign for United Kingdom |
| CoreWeave | Dedicated GPU | Bare metal, Managed Kubernetes, On-demand, Spot, Reserved capacity | United States, United Kingdom, EU/EEA | SOC 2 Type II (stated) , GDPR DPA | Per-GPU-hour on-demand and spot; reserved capacity at up to 60% discount | Not verified (United States parent) |
| Databricks Mosaic AI Model Serving(now Databricks Model Serving) | Managed self-host | Custom model serving, Provisioned throughput, Pay-per-token endpoints | United States, United Kingdom, EU/EEA, Asia-Pacific | SOC 2 Type II, ISO 27001, HIPAA BAA, FedRAMP, GDPR DPA | Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs | Stated (United States parent) |
| Fireworks AI | Dedicated GPU | Serverless, On-demand dedicated, Reserved capacity | Global, United States, EU/EEA, Asia-Pacific | SOC 2 Type II, ISO 27001 | Per 1M tokens (serverless); per-GPU-second on-demand deployments; reserved capacity | Stated (United States parent) |
| Hugging Face Inference Endpoints | Managed self-host | Dedicated endpoints, Public endpoint, Protected endpoint, Private endpoint (PrivateLink) | United States, EU/EEA | SOC 2 Type II (stated) , GDPR DPA (stated) | Per instance-hour (CPU, GPU, and accelerator instances); dedicated inference from $0.033/hour | Not verified (United States parent) |
| Modal | Dedicated GPU | Serverless, Dedicated endpoints | United States, United Kingdom, EU/EEA, Asia-Pacific | SOC 2 Type II | Per-second GPU, CPU core, and memory billing | Contractual (United States parent) |
| Nebius | Dedicated GPU | Serverless API, Dedicated endpoints | EU/EEA, United States | SOC 2 Type II (stated) , SOC 3 (stated) , ISO 27001 (stated) , GDPR DPA, HIPAA BAA | Per 1M input/output tokens; dedicated endpoints billable while a replica runs (unit not published) | Contractual (Netherlands parent) |
| NVIDIA NIM | Managed self-host | Self-hosted containers, Dedicated endpoints, NVIDIA-hosted API, DGX Cloud | Not verified | ISO 27001 (stated) , GDPR DPA | NVIDIA AI Enterprise per GPU ($4,500/GPU/year self-managed; $1/GPU/hour in cloud marketplaces plus CSP instance costs) | Not verified (United States parent) |
| OVHcloud | Managed self-host | Serverless API, Managed model deployment | EU/EEA | ISO 27001, C5, GDPR DPA (stated) | Per 1M tokens (AI Endpoints, input/output priced separately) | Contractual (France parent) Sovereign for EU/EEA |
| RunPod | Dedicated GPU | Secure Cloud, Community Cloud, Reserved clusters | United States, EU/EEA, Asia-Pacific | SOC 2 Type II, SOC 3, ISO 27001, GDPR DPA | Per GPU-hour (per-second display available); reserved clusters via sales | Stated (United States parent) |
| Scaleway Managed Inference(now Generative APIs Dedicated Deployment) | Dedicated GPU | Serverless API, Dedicated GPU inference | EU/EEA | ISO 27001, GDPR DPA | Per-hour dedicated GPU (Generative APIs Dedicated Deployment); per million tokens (Generative APIs serverless) | Contractual (France parent) Sovereign for EU/EEA |
| Together AI | Dedicated GPU | Serverless, Dedicated endpoint, GPU clusters | Not verified | SOC 2 Type II (stated) , HIPAA BAA (stated) , ISO 27001 | Per 1M tokens serverless; per GPU-hour for dedicated endpoints and clusters | Stated (United States parent) |
| Vertex AI Provisioned Throughput(now Gemini Enterprise Agent Platform Provisioned Throughput) | Hyperscaler dedicated | Provisioned throughput, Single-zone provisioned throughput | United States, EU/EEA, Asia-Pacific | SOC 2 Type II, SOC 3, ISO 27001, GDPR DPA | 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 | Contractual (United States parent) |
Three separate facts: category is how the service is delivered; parent jurisdiction is the country whose law governs the parent company; data residency is whether the vendor commits to keeping data in a chosen region, graded Contractual, Stated or Not verified. A region in one country does not change the parent's jurisdiction. "Sovereign for" is recorded only where parent, capacity, residency and the vendor's own claim all point at the same jurisdiction (how it is set; by jurisdiction).