Loading the catalogue…
Fireworks AI
L0 · Third-country operatorfireworks-aiUnited StatesNorth America
Fireworks.ai, a US company, runs an inference service for open-weight models such as DeepSeek, Kimi, GLM and Qwen. The serverless service Stav routes to runs in the United States across several GPU clouds.
Compliance posture · Stav's assessment
Jurisdiction
US · United States
Data residency
GLOBAL
CLOUD Act / FISA 702
Exposed
Stav sovereignty level
Stav's assessment
Five dimensions
Serving residency
Poor
Legal exposure
Poor
Serving retention
Adequate
Security posture
Weak
Contractual posture
Adequate
Bands only. The scores and Stav's notes per dimension are read in the workspace.
Customers only
The full assessment
Stav's narrative, every risk item with its source, the safeguards that offset them and the privacy-policy issues found: the part of the page a procurement review runs on.
Stav's narrative · 4 risk items · 5 safeguards · 1 privacy-policy issue · DPA, sub-processor list, terms, privacy policy — sign in to read them.
Traffic through Stav is covered by Stav's customer DPA, which lists Stav's sub-processors.
Stav's serving-side assessment, compiled from the provider's published documentation and Stav's operational review. Last reviewed 17 Oct 2026. An assessment, not a guarantee or regulatory determination. Confirm against the provider's own documentation before contracting.
Sovereignty ladder · how the level was reached
L0Third-country operatorIndicativeregistry 4.1
This level applies to traffic routed through Stav.
Fireworks is at L0. L1 is blocked because serverless inference runs on US infrastructure, and Fireworks.ai, Inc., a Delaware corporation, is subject to the US CLOUD Act. EU regions exist only for dedicated deployments.
3 criteria from L1: Customer data in the Union, Infrastructure in the Union, No coerced vulnerability silence.
Stav's own assessment against criterion registry 4.1. Indicative, not an official recognition, which only a national authority can confer. Criteria follow the proposed Cloud and AI Development Act and are expected to change. “Union” reads as EU/EEA at every rung. CADA itself still says “in the Union”: until the Act is incorporated into the EEA Agreement, a Norwegian, Icelandic or Liechtenstein route does not evidence formal Union assurance for an EU public-sector buyer. UK and Swiss providers are capped at L1.
Verified 17 Oct 2026About the ladder →Certifications & legal documents · the provider's own facts
SOC 2 Type II
Security, Availability, and Confidentiality trust services criteria for the inference platform · Claimed by the provider
ISO 27001
Information Security Management Systems (ISMS) · Claimed by the provider
ISO 27701
Privacy Information Management Systems (PIMS) · Claimed by the provider
ISO 42001
Artificial Intelligence Management Systems (AIMS) — responsible AI development and deployment · Claimed by the provider
HIPAA
Self-attested compliance support for healthcare/life-sciences customers (not a third-party certification) · Current
HIPAA Attestation
HIPAA compliance for healthcare and life sciences inference workloads · Claimed by the provider
PCI DSS
Not held
“Claimed by the provider” means the provider states the certification. Stav has not seen the certificate or report.
Terms of servicepublished
Privacy policypublished
Data processing agreement (DPA)published
Sub-processor listpublished
Links to every document and certificate — 4 legal documents, 7 certification sources
Compiled by Stav from the provider's published documentation. Last verified 1 Oct 2026. Reflects what the provider states, not a Stav guarantee or regulatory determination. Confirm against the provider's own pages before contracting.
Endpoints served · 11
| Model | Input / M | Output / M | TTFT | Tok/s |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | €0.20 | €0.59 | 0.53 s | 205 |
| GLM-5.3 Flash | €0.13 | €0.45 | 4.78 s | 234 |
| GLM-5.3 | €1.88 | €5.92 | 0.51 s | 342 |
| GLM-5.3 | €1.25 | €3.94 | 0.63 s | 104 |
| Qwen 3.8 Max | €1.79 | €5.38 | 0.65 s | 331 |
| Qwen3.8 2.4T A95B | €1.79 | €5.38 | 0.66 s | 336 |
| Kimi K3 | €2.69 | €13.45 | 0.88 s | 63 |
| Kimi K3 | €4.03 | €20.17 | 1.29 s | 257 |
| MiniMax: MiniMax M3 | €0.27 | €1.08 | 1.49 s | 264 |
| Qwen3 Embedding 8B | €0.09 | Free | — | — |
| Qwen3 Reranker 8B | €0.18 | Free | — | — |