Provider Directory
Confidential
Inference
Compare providers running AI inference inside trusted execution environments. Filter by models, pricing, and API features.
8 Providers
51 Models — compare by price → 8 providers
Tinfoil
TEE-Terminated TLSVerifiable private inference with Intel TDX and NVIDIA H100 CC
Models 12
From $0.05/M
OpenAI API
Streaming
Functions
Vision
NanoGPT
TEE-only GatewayPay-per-prompt confidential inference — TEE-backed models with ECDSA per-request attestation
Models 30
From $0.13/M
OpenAI API
Streaming
Functions
Vision
Redpill
Attested E2EEOpenAI-compatible confidential inference on Phala GPU TEE
Runs on Phala/dstack Models 3
From $0.15/M
OpenAI API
Streaming
Functions
Vision
Chutes
TEE-only GatewayDecentralized confidential inference on Bittensor with TEE
Models 13
From $0.02/M
OpenAI API
Streaming
Functions
Vision
NEAR AI
Attested E2EEPrivate, verifiable AI — Intel TDX + NVIDIA H200 TEE with on-chain attestation
Runs on Phala/dstack Models 13
From $0.01/M
OpenAI API
Streaming
Functions
Vision
Privatemode
Attested E2EEEU-hosted confidential inference via Cosmian VM
Models 8
From $0.15/M
OpenAI API
Streaming
Functions
Vision
PPQ.AI
Attested E2EEPrivate TEE inference via hardware-attested confidential compute
Runs on tinfoil Models 6
From $0.16/M
OpenAI API
Streaming
Functions
Vision
Venice.ai
Attested E2EEEnd-to-end encrypted private AI with TEE attestation
Runs on Phala/dstack Models 16
From $0.05/M
OpenAI API
Streaming
Functions
Vision