PPQ.AI
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.
API Features
OpenAI Compatible ✓
Streaming ✓
Function Calling ✓
Batch Inference —
Vision ✓
Embeddings —
Models & Pricing
| Model | Family | Context | Max Out | Input /M | Output /M | Free |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Moonshot AI | 256K | — | $1.57 | $5.51 | — |
| DeepSeek R1 0528 | DeepSeek | 128K | — | $1.57 | $5.51 | — |
| GPT-OSS 120B | OpenAI GPT | 128K | — | $0.79 | $1.31 | — |
| Llama 3.3 70B | Meta Llama | 128K | — | $1.84 | $2.89 | — |
| Qwen3-VL 30B | Qwen | 256K | — | $1.31 | $4.20 | — |
| GLM-5.1 | Unknown | 198K | — | $1.57 | $5.51 | — |
| Gemma 4 31B | Unknown | 256K | — | $0.47 | $1.05 | — |