Alpha
Contact
Use · DeepInfra

Is it good enough?

Ownership levelPartialnone·limited·partial·substantial·fullAnalytical input C ยท 61.6/100

This page is a projection of the one entry record, the Reliability 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 + Reliability
  • UseReliability
  • SupportTransparency

Models served

The live listing has 411 entries, of which 232 are public and not deprecated: 93 text-generation, plus image, video, speech, embedding and reranker models. Open-weight text families include:

  • DeepSeek V4 and V4.1 (Flash, Pro) and V3.x
  • Kimi K3 and K3.1 Pro
  • GLM-5.x
  • Qwen3.5
  • gpt-oss-120B and 20B
  • Gemma 4, Nemotron 3, MiMo V2.6 and Llama 3.x

94 of the 232 are flagged partner models, including nine Anthropic Claude entries and thirteen Google entries. They run on the partner's infrastructure under the partner's data policy, so treat them as a separate governance category from the hosted open catalogue.

Inference features

The endpoints are OpenAI-compatible chat/completions across the catalogue, plus embeddings, reranking, speech and media generation. Extras include per-request service tiers (Priority and Flex), prompt cache retention for 5 minutes or 1 hour on some models, and dedicated GPU instances. The model listing tags each model with capabilities such as tools and reasoning. Support for tool calling and structured output follows each model and is unverified per model, so confirm per model.

Context & token limits

The pricing page shows a context column per model - for example the DeepSeek V4 family 1024k, DeepSeek V3.2 160k, Llama 3.3 70B Turbo 128k and Gemma 4 31B 256k - and the model listing carries a max_tokens field. Limits on dedicated deployments are unverified; confirm them on the model's page before relying on a long-context workload.

How this scores

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

3

ReliabilityDoes it stay up and stay secure?

Moderate

A public status page shows measured 90-day uptime, but there is no uptime SLA or credits and no incident history page, and no independent pen-test report is verified; SOC 2 is Type 1.

How this scores (AOI sub-dimensions)
Reliability3/5whether it stays up, with an SLA and status historyA public status page (status.deepinfra.com) shows measured 90-day uptime for the API and website (100%) and per model (99.98% to 100%), a maintenance page and scheduled deprecations with replacements.
Security3/5the controls protecting your traffic and dataThe trust centre states SOC 2 and ISO 27001 as "Compliant", lists a pen-test report and ISMS manual, and shows control families (MFA, network and endpoint controls, vulnerability remediation).
Compliance3/5which independent certifications and attestations it holdsTerms Sec 5(a) incorporates a DPA by reference that applies to personal data in Customer Data without a separate signature.
What this means for adoptionYou substantially control your data on DeepInfra-hosted open models: the Terms (last modified 2026-10-15) make Zero Data Retention contractual and controlling, forbid training on it, give a mutual confidentiality duty and keep your IP, and a DPA is incorporated by reference. Ownership is capped at partial because that control is not uniform: partner models (Anthropic, Google and 90 more entries) carry the partner's data terms, so route no sensitive data through them. All processing is in the United States with no EU region, so DeepInfra is ruled out where EU data sovereignty is required. The DPA PDF and the attestation documents are unverified, so the SCC content and the SOC 2 and ISO 27001 status rest on the provider's own trust-centre statements.

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.

Documentationread2026-11-19
DeepInfra data-privacy documentation: inference input is held in memory only and deleted once inference completes.
Privacy Policyread2026-11-19
DeepInfra Privacy Policy (last modified 2026-08-15) and data-privacy docs say, for inference inputs and outputs: "We will not store, sell, or train using this data unless we have your explicit consent".
Terms of serviceread2026-11-19
DeepInfra Terms of Service (last modified 2026-10-15).
Securityread2026-11-19
DeepInfra trust centre (Sprinto): compliance badges SOC 2 "Compliant", ISO 27001 "Compliant", GDPR "In progress", HIPAA "Compliant".
Vendor announcementread2026-11-19
DeepInfra pricing page (first-party), per million tokens input / output: Llama 3.1 8B Turbo $0.02 / $0.04, Llama 3.3 70B Turbo $0.10 / $0.32.
Securityread2026-11-19
DeepInfra trust-centre FAQ (publisher statement): "All DeepInfra inference runs in data centers in the United States"; "Serverless API and dedicated deployments both run in the US only.
Documentationread2026-11-19
DeepInfra live model listing (GET https://api.deepinfra.com/models/list): 411 entries, of which 232 are public and not deprecated (93 text-generation), and 94 of those 232 carry is_partner (Anthropic 9, Google 13, Bria 20, ByteDance 9 and others).
Terms of serviceread2026-11-19
DeepInfra Terms of Service (last modified 2026-10-15).
Data Processing Addendumunverified2026-11-19
DeepInfra Data Processing Agreement: incorporated by Terms Sec 5(a) and listed on the trust centre as "2026-10-05 - Deep Infra - DPA.docx.pdf".
Subprocessorsread2026-11-19
DeepInfra sub-processor list (docs page stamped last updated 2024-09-06, and the trust centre): Stripe (payment processor), Amazon Web Services and Google Cloud Platform (infrastructure), all United States.
Documentationread2026-11-19
DeepInfra authentication docs: API keys sent as "Authorization: Bearer", each with scopes chosen at creation and editable later (a new key starts with inference, models:read, account:read, lora:read and voice:read), and short-lived scoped JWTs that can be issued to third parties.
Documentationread2026-11-19
DeepInfra rate-limits docs: rate limits apply only to public models; "every account has a default limit of 200 concurrent requests per model"; "Private dedicated endpoints have no rate limits" and return 429 Model busy when overloaded.
Slaread2026-11-19
DeepInfra status page: core services operational, all 172 monitored models operational, API and website 100% 90-day uptime over 86.4 of 90 days measured, per-model figures 99.98% to 100%, a maintenance page, and one scheduled deprecation (embeddinggemma-300m, 2026-11-23) with a named replacement.