Vendors · Comparison
Databricks Mosaic AI Model Serving (now Databricks Model Serving) vs Modal
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). Modal: Per-second GPU, CPU core, and memory billing (published pricing).
- Category Databricks Model Serving is a Managed self-host offering; Modal is Dedicated GPU.
- Compliance Both document SOC 2 Type II. Only Databricks Model Serving documents ISO 27001, HIPAA BAA, FedRAMP and GDPR DPA.
- Data residency Databricks Model Serving states data residency on its own pages (not contractual); Modal 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.
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.
Modal
Terms commit to processing customer data only in customer-specified regions. HIPAA is offered on the Enterprise plan (Volumes v2 in scope, some features out); no BAA wording was found. Dedicated Endpoints run models on isolated, autoscaling containers at standard compute rates; the pricing page lists no separate dedicated tier.
Side by side
Capabilities compared
| Databricks Mosaic AI Model Serving (now Databricks Model Serving) | Modal | |
|---|---|---|
| Pricing model | Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs | Per-second GPU, CPU core, and memory billing |
| Public pricing | Yes | Yes |
| Category | Managed self-host | Dedicated GPU |
| Deployment models | Custom model servingProvisioned throughputPay-per-token endpoints | ServerlessDedicated endpoints |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | United States, United Kingdom, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type IIISO 27001HIPAA BAAFedRAMPGDPR DPA | SOC 2 Type II |
| Data residency evidence | Stated | Contractual |
| 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. | Terms commit to processing customer data only in customer-specified regions. HIPAA is offered on the Enterprise plan (Volumes v2 in scope, some features out); no BAA wording was found. Dedicated Endpoints run models on isolated, autoscaling containers at standard compute rates; the pricing page lists no separate dedicated tier. |
Where they diverge
Deployment differentiation
Only Databricks Model Serving
Both
No overlap in deployment models.
Only Modal
Read the full profiles