NEAR AI

The Confidential TEE tier runs models on NEAR AI's own GPU fleet. Its 3P Confidential TEE and Incognito tiers route to other providers; both are excluded from this entry.

Only NEAR's own model deployments are assessed. Use canonical model IDs and verify the NEAR model evidence as well as the gateway; gateway-only verification is insufficient to identify the inference provider.

NEAR documents Intel TDX and NVIDIA confidential GPUs for its own private inference nodes. Incognito models execute outside this boundary. Third-party TEE models have different verification chains and SDK coverage.

At least one content layer has independently checkable technical evidence, including partial proof within a layer. The full privacy boundary is incomplete. The stage tooltip distinguishes partial findings from fully met requirements for Stage 2.

Identity and operational metadata are assessed separately below. They do not set the content stage; prompt or response content in telemetry remains part of the content-retention assessment.

Verified gateway. The documented gateway flow can verify fresh gateway evidence, bind the actual TLS connection and check NEAR model evidence. Standard HTTPS alone does not perform these checks. Direct completions endpoints are experimental and have verification limitations, so they are outside the assessed path.

NEAR model evidence. Verify every returned NEAR model-attestation candidate with provider=near before a completion. Canonical IDs and x-no-aliasing prevent a model alias from silently changing the assessed route. Response signatures are separate checks; their availability alone does not prove all required deployment properties.

Retention gap. Private inference documentation describes protected processing and no provider access for the scoped tier. The reviewed sources do not establish a complete lifecycle for content logs, prompt caches, stored conversations and backups. The previously indexed Cloud privacy PDF returned HTTP 404 during review; no retention guarantee is inferred from it.

Account & usage. The gateway manages API keys, authentication, usage tracking and billing. Confidential model execution does not hide these records or traffic metadata. A complete metadata retention schedule and independently checkable deletion controls were not established.

• Intel and NVIDIA hardware isolation and attestation roots.
• The verified gateway, private model-node code and client verification policy.
• Selection of NEAR's own Confidential TEE tier rather than a routed upstream model.

• The NEAR AI brand and a TEE gateway do not imply every catalog model is NEAR-hosted or confidential.
• Gateway and model verification are distinct; experimental direct endpoints have limitations.
• No live cryptographic verification or complete retention audit was performed.