Vendors · Profile
Fireworks AI
Dedicated GPUServerless and dedicated GPU inference billed per token or GPU-second
Visit Fireworks AI ↗Deployment
| Deployment models | Serverless, On-demand dedicated, Reserved capacity |
| Regions | Global, US, Europe, Asia-Pacific |
Compliance
| SOC 2 Type II docs.fireworks.ai ↗ verified 2026-07-07 |
| ISO 27001 docs.fireworks.ai ↗ verified 2026-07-07 |
| HIPAA BAA docs.fireworks.ai ↗ verified 2026-07-07 |
| Pricing model | Per 1M tokens (serverless); per-GPU-second on-demand deployments; reserved capacity |
| Public pricing | Yes |
| Data residency guarantee | Not verified |
| Parent jurisdiction | US |
Analyst note
On-demand deployments run on dedicated GPUs with region selection (US, Europe, APAC). No public data-residency guarantee found at review; the privacy policy states servers are in the US with SCCs for cross-border transfers. ISO 27701/42001 also claimed in vendor docs.
Compare Fireworks AI vs…
- Comparison Fireworks AI vs Amazon Bedrock Provisioned Throughput
- Comparison Fireworks AI vs Azure OpenAI Provisioned Throughput (PTU)
- Comparison Fireworks AI vs Baseten
- Comparison Fireworks AI vs Civo
- Comparison Fireworks AI vs CoreWeave
- Comparison Fireworks AI vs Databricks Model Serving
- Comparison Fireworks AI vs Hugging Face Inference Endpoints
- Comparison Fireworks AI vs Modal
- Comparison Fireworks AI vs Nebius
- Comparison Fireworks AI vs NVIDIA NIM
- Comparison Fireworks AI vs OVHcloud
- Comparison Fireworks AI vs RunPod
- Comparison Fireworks AI vs Scaleway
- Comparison Fireworks AI vs Together AI
- Comparison Fireworks AI vs Vertex AI Provisioned Throughput