Confidential AI

Declared: TEE-Terminated TLS

Confidential inference on Intel TDX with a nonce-bound, TLS-bound front-door attestation

Confidential AI (Inexorable, Inc.) serves open-weight models inside Intel TDX confidential VMs on its open-source c8s platform, with NVIDIA GPUs in confidential-compute mode. The public /.well-known/c8s/attest-lb endpoint returns a fresh nonce-bound Intel TDX quote for the cluster's front door that binds the live TLS serving certificate, the mesh identity and the route table digest. The signed release bundle publishes the node image measurements and the workload allowlist; GPUs are checked by a measured-boot gate before a node joins, and raw GPU reports are not served.

Models1

Input from$0.30/M input tokens (declared)

Organization rolesStorefront · Workload operator · TEE platform

Trust chainIntel (TDX) + NVIDIA (GPU CC) · CPU TEE in path: yes · physical attacks

Advertised ChannelTEE-Terminated TLS

Post-Quantum KEXHybrid TLS observedX25519MLKEM768 · measured 2026-11-10 · PQC run #56

API Features

OpenAI Compatible✓

Streaming✓

Function Calling—

Batch Inference—

Vision—

Embeddings—

Attestation Status

View full details →

Latest attempt: Checked · observed Nov 10, 2026, 12:00:42 UTC

Latest attempt complete; discovery complete; 1/1 targets completed

Model coverage: 0/1 current catalog models have an explicit check.

Incomplete evidenceHardware evidence may have passed, but one or more required evidence gates are excluded or not proven.

0 verified1 incomplete0 failed0 unavailable

Hardware1/1 goodTCB policy1/1 goodFreshness1/1 goodChannel binding1/1 goodWorkload identity1 warningSource provenance1 warningRequest route1 warningAvailability1/1 good

Workload identity not proven 1Source provenance not proven 1Request route not proven 1

◐Confidential AI cluster (c8s)Intel TDXTEE-Terminated TLSDetails

Get notified when this provider's attestation verdict changes:Alerts RSS

Models & Pricing

Rates are exactly what the provider source published, kept in the recorded currency; USD eligibility is evaluated from fresh observations. Declared conditions and undisclosed terms are listed, not verified.

Model / source ID	Family	Context	Max Out	Offerings	Attestation	Observed route
DeepSeek V4.1 Flash 1017deepseek-ai/DeepSeek-V4.1-Flash-1017	DeepSeek	—	—	per tokens`deepseek-ai/DeepSeek-V4.1-Flash-1017#tokens` In $0.30 /M · out $1.20 /M declared declared price source · observed 2026-11-09 · price source Cached input $0.03 per 1M tokens. Listed as Available on the public pricing page (prices as of 9 Nov 2026).	No current check	Not identified