All Providers

Tinfoil

TEE-Terminated TLS

Verifiable private inference with Intel TDX and NVIDIA H100 CC

Tinfoil provides confidential inference with hardware-attestable privacy guarantees. Every request runs inside an Intel TDX enclave or on an NVIDIA H100 Confidential Computing GPU. Users can cryptographically verify that their prompts are processed in a trusted execution environment and never exposed to the host operator.

HQ San Francisco, CA
Models 12
From $0.05/M input tokens
Trust Tier TEE-Terminated TLS

API Features

OpenAI Compatible
Streaming
Function Calling
Batch Inference
Vision
Embeddings

Attestation Status

View full details →

Last checked: Jul 12, 2026, 12:01 AM

Availability issue The verifier could not fetch fresh evidence for every check in this run.
7 verified 0 partial 0 failed 2 unavailable
Hardware 7/9 good Freshness Not shown Key binding 6/9 good Workload Not shown Provenance 7/9 good Availability 2 warning
Endpoint unavailable 2
Get notified when this provider's attestation verdict changes: Alerts RSS

Models & Pricing

Model Family Context Max Out Input /M Output /M Free
Kimi K2.6 Moonshot AI 256K $1.50 $5.25
GLM 5.2 ZhipuAI GLM 384K $1.50 $5.25
Gemma 4 31B Google Gemma 256K $0.40 $1.00
Llama 3.3 70B Meta Llama 128K $1.75 $2.75
GPT-OSS 120B OpenAI GPT 128K $0.15 $0.60
GPT-OSS Safeguard 120B OpenAI GPT 128K $0.15 $0.60
Nomic Embed Text Nomic 8K $0.05 $0.00
Voxtral Small 24B Mistral 32K $0.20 $0.60
Whisper Large V3 Turbo OpenAI GPT 29K $0.01/request
Qwen3-TTS 1.7B Qwen 4K $0.01/request
Voxtral Tts Mistral 4K $0.002/request
Voxtral Mini 4B Realtime Mistral 4K $0.002/request