All Providers

PPQ.AI

Attested E2EE

Private TEE inference via hardware-attested confidential compute

PPQ.AI is a multi-model AI API platform that offers a dedicated private inference tier running inside hardware Trusted Execution Environments. Models prefixed with 'private/' execute in isolated enclaves with hardware attestation, ensuring that prompts and outputs remain confidential throughout the inference process.

Models 6
From $0.16/M input tokens
Organization roles Storefront · Aggregator
E2EE HPKE
Advertised Channel Attested E2EE

API Features

OpenAI Compatible
Streaming
Function Calling
Batch Inference
Vision
Embeddings

Attestation Status

View full details →

Last checked: Aug 7, 2026, 12:01 PM

Model coverage: 6/6 current catalog models have an explicit check.

Incomplete evidence Hardware and TCB passed, but one or more later evidence gates are not proven.
0 verified 1 partial 0 failed 5 unavailable
Hardware 5 warning TCB policy 5 warning Freshness 6 warning Channel binding 5 warning Workload identity 6 warning Source provenance 6 warning Request route 6 warning Availability 5 warning
Endpoint unavailable 5 Freshness not proven 1 Workload identity not proven 1 Source provenance not proven 1
Get notified when this provider's attestation verdict changes: Alerts RSS

Models & Pricing

Model Family Context Max Out Input /M Output /M Free Attestation Observed route
GPT-OSS 120B OpenAI GPT 128K $0.16 $0.63 unreachable Tinfoil declared · route not bound
Llama 3.3 70B Meta Llama 128K $1.85 $2.90 unreachable Tinfoil declared · route not bound
Qwen3-VL 30B A3B Qwen 256K $1.32 $4.22 unreachable Tinfoil declared · route not bound
GLM 5.2 ZhipuAI GLM 375K $1.58 $5.54 partial Tinfoil declared · route not bound
Gemma 4 31B Google Gemma 256K $0.42 $1.05 unreachable Tinfoil declared · route not bound
Kimi K2.6 Moonshot AI 256K $1.58 $5.54 unreachable Tinfoil declared · route not bound