Ctrl K
Contact
Use · DeepInfra

Is it good enough?

Ownership levelPartialnone·limited·partial·substantial·fullAnalytical input C ยท 60.4/100

This page is a projection of the one entry record, the Doesn't fail you factor that Use covers. The full verdict is set by all four factors together, floor-weighted so the weakest caps the whole.

Which domain expands which factor
  • AssessUse & modify + Transparency
  • ImplementData control + Doesn't fail you
  • UseDoesn't fail you
  • SupportTransparency

Models served

DeepInfra serves a broad open catalogue of ~77-90+ models rather than a single family:

  • Llama 3.x / 4.x
  • DeepSeek V3 / V3.2 / V4 variants
  • Qwen3
  • Kimi K2
  • GLM-5
  • gpt-oss-120B
  • MiniMax-M2
  • Nemotron
  • Gemma

It also re-sells some closed models (Anthropic Claude, Google) - useful for reach, but these are not portable and route your data under those vendors' terms, so treat them as a separate governance category from the open catalogue.

Inference features

The endpoints are OpenAI-compatible chat/completions across the catalogue, with per-hour dedicated GPU instances available for reserved throughput. Higher-level behaviours such as tool/function calling and structured (JSON) output depend on each served model's own capabilities - see the model's entry in this library - and were not individually re-verified on DeepInfra's endpoints this session, so treat per-feature support as "inherited from the model, confirm per model."

How this scores

The ownership factor this domain covers, drawn from the one entry record.

3

Doesn't fail youDoes it stay up and stay secure?

Moderate

SOC 2 and ISO 27001 certification give baseline controls, but the Type designation is unverified and no public uptime SLA, status page or independent pen-test was found.

How this scores (AOI sub-dimensions)
Reliability2/5whether it stays up, with an SLA and status historyNo incidents surfaced, but no public uptime SLA, status page or failover documentation was independently verified.
Security3/5the controls protecting your traffic and dataISO 27001 and SOC 2 certification indicate baseline controls, and the retrieved data-privacy documentation confirms batch data is held encrypted on disk then deleted.
Compliance3/5which independent certifications and attestations it holdsSOC 2 and ISO 27001 certification plus GDPR/HIPAA technical and organisational measures are stated on the retrieved data-privacy documentation, meeting the "SOC 2 or ISO 27001 + DPA" anchor.
What this means for adoptionYou substantially control your data on DeepInfra's own open-model serving: the retrieved Terms let you keep IP over your Submissions, and zero-retention plus no-training keep inputs and outputs yours, with the open checkpoints a clean portable exit. Ownership is capped at partial because that control is not uniform - the re-sold closed models (Claude, Google) are transferred to those vendors and carry their data terms, not DeepInfra's, so route no sensitive data through them - and US-only residency rules it out where EU data sovereignty is required.

Sources

The same evidence records as the entry sheet. Read means the text was verified; unverified means it is known to exist but not yet read.

Documentationread2026-07-25
DeepInfra data-privacy documentation: zero-retention by default, only debugging metadata (request ID, cost, sampling parameters) is logged, batch/bulk data is held encrypted on disk then deleted after a short retention period, it does not train on submitted data, it runs on secure US-based data centres, and it is SOC 2 and ISO 27001 certified.
Privacy Policyread2026-07-25
DeepInfra data-privacy statement: it does not use API data for training except when using Google or Anthropic models, where the receiving company's training policy applies - if you use a Google model, Google stores the output per its Privacy Notice; if you use an Anthropic model, Anthropic stores the output per its Trust Centre.
Terms of serviceread2026-07-25
DeepInfra Terms of Service: 'When you submit data, content, materials, or requests into models through DeepInfra (Submissions), you retain any intellectual property rights over such Submissions, which will remain private'; DeepInfra does not share data with third parties except when using Google or Anthropic models, where it is required to transfer data to those endpoints to fulfil the request.
Securityunverified2026-07-25
Trust centre (Sprinto-powered) is stated to list SOC 2 Type 1 (not Type II) and ISO 27001; the SOC 2 Type designation, sub-processor list and ISO 27701 status were not read verbatim this session - documented but unverified.
Third-party analysisunverified2026-07-25
Among the cheapest providers (third-party pricing research): per-token e.g.
Documentationread2026-07-25
DeepInfra data-privacy documentation states it runs on secure US-based data centres; no EU data-residency option was surfaced.
Third-party analysisunverified2026-07-25
Serves ~77-90+ open models over an OpenAI-compatible API on NVIDIA GPUs plus per-hour GPU instances; also re-sells some closed models (Anthropic Claude, Google).