Loading the catalogue…
DeepInfra
L0 · Third-country operatordeepinfraUnited StatesNorth America
DeepInfra, Inc. (Palo Alto, California) runs serverless inference for a large catalogue of open-weight models in US data centers, over an OpenAI-compatible API. Its terms commit to zero data retention and no training on customer data.
Compliance posture · Stav's assessment
Jurisdiction
US · United States
Data residency
UNKNOWN
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
Weak
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 · 6 risk items · 7 safeguards · 4 privacy-policy issues · 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.
DeepInfra is at L0. L1 is blocked because data and infrastructure are in eight US data centers with no EU/EEA option, and as a US company it can be compelled under the CLOUD Act and FISA.
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 I
Service organization controls (as published on DeepInfra's Trust Center resources list as 'Deep Infra SOC 2 Type 1 Report') · Claimed by the provider
ISO 27001
Information security management system (listed on DeepInfra's Trust Center resources as 'Deep Infra ISO 27001 Certificate'; edition not stated) · Claimed by the provider
HIPAA
Technical and organizational safeguards for protected health information · Current
GDPR
EU data protection compliance program · In progress
“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)not published
Sub-processor listpublished
Links to every document and certificate — 3 legal documents, 4 certification sources
Compiled by Stav from the provider's published documentation. Last verified 28 Sept 2026. Reflects what the provider states, not a Stav guarantee or regulatory determination. Confirm against the provider's own pages before contracting.
Endpoints served · 19
| Model | Input / M | Output / M | TTFT | Tok/s |
|---|---|---|---|---|
| MiMo-V2.6-Flash | €0.13 | €0.25 | 0.83 s | 110 |
| MiMo-V2.6-Pro | €0.39 | €0.78 | 0.68 s | 65 |
| DeepSeek V4.1 Flash | €0.18 | €0.54 | 2.72 s | 225 |
| GLM-5.3 Flash | €0.13 | €0.45 | 1.37 s | 41 |
| GLM-5.3 | €0.81 | €3.59 | 1.00 s | 208 |
| DeepSeek V4 Pro (0813) | €1.17 | €2.33 | 0.72 s | 184 |
| DeepSeek V4 Flash (0731) | €0.05 | €0.16 | 0.85 s | 66 |
| Kimi K3 | €2.55 | €12.77 | 0.80 s | 37 |
| glm-5-2 | €0.67 | €2.15 | 0.78 s | 204 |
| qwen3.6-35b-a3b | €0.09 | €0.85 | 0.82 s | 74 |
| Gemma 4 26B A4B It | €0.06 | €0.30 | 1.18 s | 57 |
| Gemma 4 31B It | €0.18 | €0.36 | 1.07 s | 16 |
| NVIDIA-Nemotron-3-Super-120B-A12B | €0.07 | €0.36 | 0.67 s | 111 |
| qwen3.5-397b-a17b | €0.40 | €2.69 | 0.57 s | 43 |
| gpt-oss-20b | €0.03 | €0.13 | 0.68 s | 98 |
| Mistral-Small-3.2-24B-Instruct-2506 | €0.07 | €0.18 | 2.34 s | 18 |
| bge-m3 | €0.01 | Free | 0.97 s | 0 |
| gpt-oss-120b | €0.03 | €0.15 | 0.58 s | 65 |
| qwen3.8-27b | €0.18 | €2.24 | 0.67 s | 31 |