Loading the catalogue…
Loading the catalogue…
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.
Five dimensions
Bands only. The scores and Stav's notes per dimension are read in the workspace.
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.
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 →“Claimed by the provider” means the provider states the certification. Stav has not seen the certificate or report.
| 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 | €2.56 | €12.79 | 0.80 s | 37 |
| glm-5-2 | €0.67 | €2.15 | 0.78 s | 204 |
| Gemma 4 26B A4B It | €0.06 | €0.31 | 1.18 s | 57 |
| Gemma 4 31B It | €0.18 | €0.36 | 1.07 s | 16 |
| Mistral-Small-3.2-24B-Instruct-2506 | €0.07 | €0.18 | 2.34 s | 18 |
| gpt-oss-120b | €0.03 | €0.15 | 0.58 s | 65 |