Vendors · Comparison
Databricks Mosaic AI Model Serving (now Databricks Model Serving) vs Hugging Face Inference Endpoints
Only Databricks Model Serving documents ISO 27001, HIPAA BAA and FedRAMP. 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 Databricks Model Serving: Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs (published pricing). Hugging Face Inference Endpoints: Per instance-hour (CPU, GPU, and accelerator instances); dedicated inference from $0.033/hour (published pricing).
- Category Both are Managed self-host offerings.
- Compliance Both document SOC 2 Type II and GDPR DPA. Only Databricks Model Serving documents ISO 27001, HIPAA BAA and FedRAMP.
- Data residency Databricks Model Serving states data residency on its own pages (not contractual); Hugging Face Inference Endpoints's data residency is not verified.
- Jurisdiction Both parent companies are under United States jurisdiction.
Generated from the verified vendor data below; sources and dates on each vendor profile.
Databricks Mosaic AI Model Serving (now Databricks Model Serving)
Model Serving deploys custom MLflow models and fine-tuned foundation models on Databricks-managed serverless compute; provisioned throughput allocates dedicated inference capacity. Trust pages list ISO 27001:2022 (including AWS single-tenant), SOC 2 Type II, HIPAA options and FedRAMP Class C and D (formerly Moderate and High). A standard BAA and a DPA with SCCs are published.
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.
Side by side
Capabilities compared
| Databricks Mosaic AI Model Serving (now Databricks Model Serving) | Hugging Face Inference Endpoints | |
|---|---|---|
| Pricing model | Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs | Per instance-hour (CPU, GPU, and accelerator instances); dedicated inference from $0.033/hour |
| Public pricing | Yes | Yes |
| Category | Managed self-host | Managed self-host |
| Deployment models | Custom model servingProvisioned throughputPay-per-token endpoints | Dedicated endpointsPublic endpointProtected endpointPrivate endpoint (PrivateLink) |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | United States, EU/EEA |
| Compliance | SOC 2 Type IIISO 27001HIPAA BAAFedRAMPGDPR DPA | SOC 2 Type II (stated)GDPR DPA (stated) |
| Data residency evidence | Stated | Not verified |
| Parent jurisdiction | United States | United States |
| Sovereign for | Not recorded | Not recorded |
| Analyst note | Model Serving deploys custom MLflow models and fine-tuned foundation models on Databricks-managed serverless compute; provisioned throughput allocates dedicated inference capacity. Trust pages list ISO 27001:2022 (including AWS single-tenant), SOC 2 Type II, HIPAA options and FedRAMP Class C and D (formerly Moderate and High). A standard BAA and a DPA with SCCs are published. | 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. |
Where they diverge
Deployment differentiation
Only Databricks Model Serving
Both
No overlap in deployment models.
Only Hugging Face Inference Endpoints