Vendors · Comparison
Amazon Bedrock Provisioned Throughput vs Fireworks AI
Fireworks AI publishes its prices; Bedrock Provisioned Throughput has no full public price list. Pricing, compliance and residency 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). Fireworks AI: Per 1M tokens (serverless); per-GPU-second on-demand deployments; reserved capacity (published pricing).
- Category Amazon Bedrock Provisioned Throughput is a Hyperscaler dedicated offering; Fireworks AI is Dedicated GPU.
- Compliance Both document SOC 2 Type II and ISO 27001. Only Amazon Bedrock Provisioned Throughput documents SOC 3, HIPAA BAA, C5, FedRAMP and GDPR DPA.
- Data residency Amazon Bedrock Provisioned Throughput commits to data residency in its contract terms; Fireworks AI 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.
Fireworks AI
On-demand deployments run on dedicated GPUs with region selection (US, Europe, APAC). Enterprise accounts can enforce US-only inference account-wide, a product setting rather than a contract term. The trust centre lists HIPAA, but no BAA was found. ISO 27701/42001 also claimed.
Side by side
Capabilities compared
| Amazon Bedrock Provisioned Throughput | Fireworks AI | |
|---|---|---|
| Pricing model | Per Model Unit (MU) per hour; no-commitment, 1-month, or 6-month terms | Per 1M tokens (serverless); per-GPU-second on-demand deployments; reserved capacity |
| Public pricing | No | Yes |
| Category | Hyperscaler dedicated | Dedicated GPU |
| Deployment models | Provisioned throughputCustom model (provisioned) | ServerlessOn-demand dedicatedReserved capacity |
| Regions | United States, United Kingdom, EU/EEA, Asia-Pacific | Global, United States, EU/EEA, Asia-Pacific |
| Compliance | SOC 2 Type IISOC 3ISO 27001HIPAA BAAC5FedRAMPGDPR DPA | SOC 2 Type IIISO 27001 |
| 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. | On-demand deployments run on dedicated GPUs with region selection (US, Europe, APAC). Enterprise accounts can enforce US-only inference account-wide, a product setting rather than a contract term. The trust centre lists HIPAA, but no BAA was found. ISO 27701/42001 also claimed. |
Where they diverge
Deployment differentiation
Only Amazon Bedrock Provisioned Throughput
Both
No overlap in deployment models.
Only Fireworks AI
Read the full profiles