singletenant.ai

Vendors · Comparison

Amazon Bedrock Provisioned Throughput vs Databricks Model Serving

Side-by-side comparison of Amazon Bedrock Provisioned Throughput and Databricks Model Serving for single-tenant LLM hosting. Deployment options, compliance, pricing, and operational fit compared.

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 Model Serving

Mosaic AI 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 report on request, HIPAA options, FedRAMP Moderate/High; a standard BAA is published. DPA with SCCs published. Databricks, Inc. is headquartered in San Francisco.

From the data

Key differences

  • 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 has a verified residency guarantee; Databricks Model Serving's residency guarantee is not verified.
  • Jurisdiction Both parent companies are under US jurisdiction.
  • 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).

Generated from the verified vendor data below; sources and dates on each vendor profile.

Side by side

Capabilities compared

Amazon Bedrock Provisioned Throughput Databricks Model Serving
Category Hyperscaler dedicated Managed self-host
Deployment models Provisioned throughputCustom model (provisioned) Custom model servingProvisioned throughputPay-per-token endpoints
Regions US, Europe, Asia-Pacific US, Europe, Asia-Pacific
Compliance SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA SOC 2 Type IIISO 27001HIPAA BAAFedRAMPGDPR DPA
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
Residency guarantee Yes Not verified
Parent jurisdiction US US
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. Mosaic AI 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 report on request, HIPAA options, FedRAMP Moderate/High; a standard BAA is published. DPA with SCCs published. Databricks, Inc. is headquartered in San Francisco.

Where they diverge

Deployment differentiation

Only Amazon Bedrock Provisioned Throughput

Custom model (provisioned)

Both

Provisioned throughput

Only Databricks Model Serving

Custom model servingPay-per-token endpoints

Read the full profiles