Vendors · Comparison
Amazon Bedrock Provisioned Throughput vs Databricks Mosaic AI Model Serving (now Databricks Model Serving)
Databricks Model Serving publishes its prices; Bedrock Provisioned Throughput has no full public price list. Compared with sources.
Last verified (older of the two profiles) How we verify
From the data
Key differences
- Pricing Amazon Bedrock Provisioned Throughput: Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms (no published 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).
- Category Amazon Bedrock Provisioned Throughput is a Hyperscaler dedicated offering; Databricks Model Serving is Managed self-host.
- Compliance Both document SOC 2 Type II, ISO 27001, HIPAA BAA, FedRAMP and GDPR DPA. Only Amazon Bedrock Provisioned Throughput documents SOC 3 and C5.
- Data residency Amazon Bedrock Provisioned Throughput commits to data residency in its contract terms; Databricks Model Serving states data residency on its own pages (not contractual).
- Jurisdiction Both parent companies are under United States jurisdiction.
Generated from the verified vendor data below; sources and dates on each vendor profile.
Amazon Bedrock Provisioned Throughput
Provisioned Throughput reserves per-model capacity in Model Units (MUs), billed hourly with no-commitment, 1-month, or 6-month terms; required for serving customised models. AWS states Bedrock content is stored at rest in the Region of use and not shared with model providers. Example per-MU rates are published for some models; most quotes require an AWS account team.
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.
Side by side
Capabilities compared
| Amazon Bedrock Provisioned Throughput | Databricks Mosaic AI Model Serving (now Databricks Model Serving) | |
|---|---|---|
| Pricing model | Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms | Per DBU per hour by GPU instance size (e.g. A10G 20 DBU/hour); per-token Foundation Model APIs |
| Public pricing | No | Yes |
| Category | Hyperscaler dedicated | Managed self-host |
| Deployment models | Provisioned throughputCustom model (provisioned) | Custom model servingProvisioned throughputPay-per-token endpoints |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | United States, United Kingdom, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA | SOC 2 Type IIISO 27001HIPAA BAAFedRAMPGDPR DPA |
| Data residency evidence | Contractual | Stated |
| Parent jurisdiction | United States | United States |
| Sovereign for | Not recorded | Not recorded |
| Analyst note | Provisioned Throughput reserves per-model capacity in Model Units (MUs), billed hourly with no-commitment, 1-month, or 6-month terms; required for serving customised models. AWS states Bedrock content is stored at rest in the Region of use and not shared with model providers. Example per-MU rates are published for some models; most quotes require an AWS account team. | 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. |
Where they diverge
Deployment differentiation
Only Amazon Bedrock Provisioned Throughput
Both
Only Databricks Model Serving