Tinfoil
TEE-Terminated TLSVerifiable 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.
API Features
OpenAI Compatible✓
Streaming✓
Function Calling✓
Batch Inference—
Vision✓
Embeddings✓
Attestation Status
View full details →Last checked: Oct 10, 2026, 3:01 PM
Model coverage: 8/14 current catalog models have an explicit check.
Availability issueThe verifier could not fetch fresh evidence for every check in this run.
1 verified0 partial0 failed8 unavailable
Hardware9/9 goodTCB policy9/9 goodFreshness8 warningChannel binding8/9 goodWorkload identity8 warningSource provenance8 warningRequest route8 warningAvailability8 warning
Endpoint unavailable 8
DeepSeek V4.1 Flash (router-verified)AMD SEV-SNPTinfoil · declaredDetailsGemma4 31B (router-verified)AMD SEV-SNPTinfoil · declaredDetailsGLM 5.3 (router-verified)AMD SEV-SNPTinfoil · declaredDetailsGPT OSS 120B (router-verified)AMD SEV-SNPTinfoil · declaredDetailsGPT OSS Safeguard 120B (router-verified)AMD SEV-SNPTinfoil · declaredDetailsKimi K3 (router-verified)AMD SEV-SNPTinfoil · declaredDetailsLlama3.3 70B (router-verified)AMD SEV-SNPTinfoil · declaredDetailsPii Filter (router-verified)AMD SEV-SNPTinfoil · declaredDetailsRouterAMD SEV-SNPTEE-only GatewayTinfoil · verifiedDetails
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 |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | 4K | — | $0.65 | $1.45 | — | unreachable | Tinfoildeclared · route not bound |
| GLM 5.3 | ZhipuAI GLM | 4K | — | $1.80 | $5.75 | — | unreachable | Tinfoildeclared · route not bound |
| Kimi K3 | Moonshot AI | 4K | — | $4.00 | $20.00 | — | unreachable | Tinfoildeclared · route not bound |
| Llama 3.3 70B | Meta Llama | 128K | — | $1.75 | $2.75 | — | unreachable | Tinfoildeclared · route not bound |
| Gemma 4 31B | Google Gemma | 4K | — | $0.40 | $1.00 | — | unreachable | Tinfoildeclared · route not bound |
| GPT-OSS 120B | OpenAI GPT | 128K | — | $0.15 | $0.60 | — | unreachable | Tinfoildeclared · route not bound |
| GPT-OSS Safeguard 120B | OpenAI GPT | 128K | — | $0.15 | $0.60 | — | unreachable | Tinfoildeclared · route not bound |
| Pii Filter | Unknown | 4K | — | $0.005/request | — | — | unreachable | Tinfoildeclared · route not bound |
| Nomic Embed Text | Nomic | 8K | — | $0.05 | $0.00 | — | No current check | Not identified |
| Voxtral Small 24B | Mistral | 32K | — | $0.20 | $0.60 | — | No current check | Not identified |
| Whisper Large V3 Turbo | OpenAI GPT | 29K | — | $0.01/request | — | — | No current check | Not identified |
| Qwen3-TTS 1.7B | Qwen | 4K | — | $0.01/request | — | — | No current check | Not identified |
| Voxtral Tts | Mistral | 4K | — | $0.002/request | — | — | No current check | Not identified |
| Voxtral Mini 4B Realtime | Mistral | 4K | — | $0.002/request | — | — | No current check | Not identified |