# NEAR AI Cloud: private AI inference you can verify

Updated: 2026-11-16
Canonical page: https://near.ai/

## What is NEAR AI Cloud?

NEAR AI Cloud is private AI inference you can verify: open-weight models run inside hardware-secured trusted execution environments (TEEs) built on Intel and NVIDIA confidential computing. Every response is signed inside the enclave and backed by a hardware attestation, so you can check what served your prompt instead of trusting a policy promise.

## How it works

1. **You encrypt the request.** Prompts are sent over TLS and only decrypted inside the enclave. Keys never touch our infrastructure.
2. **It runs inside a TEE.** Inference executes in an Intel TDX + NVIDIA confidential-GPU enclave. Memory is sealed from the host and operators.
3. **The hardware signs a proof.** The TEE produces a cryptographic attestation quote binding the exact model and code that ran.
4. **You verify the result.** Check the attestation yourself, in code or with our open verifier. Trust the math, not a promise.

## Why teams trust it

- **Confidential GPU compute.** Models run on NVIDIA confidential computing inside Intel TDX. Data stays encrypted in use, not just at rest and in transit.
- **Attestation on every call.** Each response carries a verifiable hardware quote binding the exact code and weights that served it.
- **Open source & auditable.** The runtime, verifier, and enclave images are open. Reproduce the build and check it yourself.
- **OpenAI-compatible API.** Drop-in replacement for the OpenAI SDK. Swap the base URL and your stack keeps working.
- **No vendor lock-in.** Open weights and open models. Bring your own, or pick from a growing catalog, portable by design.
- **You hold the keys.** Client-held encryption keys. We never see plaintext, and there is no operator backdoor, by construction.

## Terms

- **Trusted execution environment** (TEE, secure enclave): A hardware-isolated region of a CPU or GPU where code and data stay encrypted even while running, so the host machine and its operator cannot read them.
- **Confidential computing** (confidential AI, confidential inference): Processing data inside hardware-secured enclaves, such as Intel TDX and NVIDIA confidential GPUs, so it stays protected while in use, not only at rest or in transit.
- **Attestation** (remote attestation, hardware attestation): A hardware-signed proof of exactly what code and model ran, and that they ran inside a sealed enclave. Anyone can verify it independently.

## Pricing

Per token, priced separately for input and output, with no minimums or subscriptions. Private execution and attestation are included in the rate.
Per-model rates in plain text: https://near.ai/pricing.md

## Questions

### What exactly is a TEE, and why does it matter?

A Trusted Execution Environment is a hardware-isolated region of a CPU/GPU where code and data are encrypted even while running. It means your prompts and the model can be processed without the host machine, the operator, or NEAR AI ever being able to read them.

### How is this different from a normal “private” API?

Most providers promise privacy in their terms of service. NEAR AI Cloud gives you a cryptographic attestation, a hardware-signed proof of exactly what code ran and that it ran inside a sealed enclave. You verify it yourself; you don’t take our word for it.

### Do I need to change my code?

No. The API is OpenAI-compatible. Point your existing OpenAI SDK at our base URL, add your key, and you keep attestation as a bonus you can optionally verify.

### Is it really open source?

Yes. The enclave runtime, the attestation verifier, and the model images are open and reproducible, so you can audit the full path your data takes.

### Which models are supported?

A growing catalog of open-weight models such as GLM and Qwen, served privately in secure enclaves. Bring-your-own and private models are available on Team and Enterprise plans.

## Links

- Models: https://near.ai/models (plain text: https://near.ai/models.md)
- Documentation: https://docs.near.ai/cloud/introduction
- Attestation and verification: https://docs.near.ai/cloud/verification
- Console (create an API key): https://cloud.near.ai
- Site map for language models: https://near.ai/llms.txt
