NEAR AI
Sign inStart building

What is private AI inference?

Private AI inference means running an AI model so that nobody but you can read your prompts and the answers, not the cloud provider, not the model provider and not the company serving the model. The model runs inside a trusted execution environment (TEE), a sealed area of the CPU and GPU that keeps data encrypted from the machine's own operator. The hardware signs a report of what is running, so you can verify the privacy instead of trusting a policy.

Requests sealed in the enclave
Private AI vs ChatGPT

Is ChatGPT private? Is it encrypted?

ChatGPT encrypts your conversations in transit and at rest (OpenAI). That protects them from outsiders. It does not protect them from OpenAI: the service holds the keys and processes your conversations in readable form. It is not end-to-end encrypted.

On the Free, Plus and Pro plans, OpenAI says it may use your content to train its models unless you turn off "Improve the model for everyone" (OpenAI Help Center).

  • Encryption in transit and at rest stops outsiders
  • It does not stop the provider. Private inference does
How private inference works

Four steps. Each one you can check.

  1. [ 01 ]

    Encrypted on your machine

    You call the API over HTTPS, as with any OpenAI-compatible API. The encrypted connection ends inside the gateway's own enclave, not at a load balancer the provider's staff can read.

  2. [ 02 ]

    Run in sealed hardware

    The gateway forwards the request to a model running in an Intel TDX confidential virtual machine with an NVIDIA GPU in confidential computing mode. Memory stays encrypted, so the host, the cloud provider and NEAR AI cannot read the prompt or the answer.

  3. [ 03 ]

    Signed by the hardware

    Each enclave produces an attestation report: a statement of the exact hardware and code it runs, signed by keys rooted in Intel and NVIDIA, not in NEAR AI. Responses can carry a signature from a key that never leaves the enclave.

  4. [ 04 ]

    Checked by you

    You verify the report against Intel's and NVIDIA's attestation services, compare the code measurement with the published source, and check the response signature. If any check fails, you know before you trust the answer.

Sources: NEAR AI private inference docs, Intel TDX and NVIDIA confidential computing.

Compared

Private inference vs a typical AI API vs running it yourself

Typical AI APIPrivate inferenceSelf-hosted
Who can read your promptsThe provider, and anyone with access to its serversNobody but you. The operator cannot see into the enclaveYou, and whoever runs your servers
What you rely onA privacy policy and a contractHardware isolation you can verifyYour own security
ProofNone you can checkA signed hardware attestation for each deploymentYour own audit
SetupAn API keyAn API key. Same OpenAI-compatible APIGPUs, model serving and upkeep
ModelsClosed and open modelsOpen-weight modelsOpen-weight models that fit your hardware

Keeping data in one cloud region is not the same thing. The region decides where your data sits. It does not decide who can read it.

Verification

Don't trust it. Verify it.

A privacy policy asks you to trust the provider. Attestation lets you check. Three ways to verify NEAR AI Cloud, from no code to full control:

  • In the browser. The Verification Center shows a model's hardware attestation and checks a reply's signature, with no code.
  • In your code. Request a fresh attestation report with your own random nonce, then check it with the verification guides and the open-source verifier.
  • From the source. The enclave software, the Private ML SDK, is open source. The attestation includes a measurement of the exact code running, so you can match it to the published build.

Intel and NVIDIA sign the evidence, not NEAR AI. You never have to take our word for it.

Limits

What private inference does not protect

  • TEEs are not magic. Researchers have published attacks on TEEs before. They make reading your data far harder and far more costly, and attestation shows you what is running. They do not make attacks impossible.
  • Only models in a TEE are private. On NEAR AI Cloud, models marked Private TEE or Private 3P TEE run in enclaves. Models marked Incognito run at their provider: NEAR AI hides your account, but there is no hardware guarantee.
  • Your own systems still matter. Private inference protects the request while the model runs. What you log, store or send elsewhere is up to you.
Who uses it

For data you can't hand over.

  • Code assistants

    Your source code is in every prompt a coding agent sends. Private inference keeps it out of anyone else's reach.

  • Regulated data

    Health, legal and financial teams can send client data to a model without handing it to a third party in readable form.

  • Security research

    Security teams analyze exploits and hostile code with uncensored models without exposing their findings. See security research on NEAR AI Cloud.

  • Products built on AI

    Apps and agents can promise their users privacy and prove it. Brave Leo runs on private inference from NEAR AI Cloud.

Use it through our API

Private inference with the API you already use.

NEAR AI Cloud runs open-weight models in TEEs behind an OpenAI-compatible API. Change the base URL and the key, keep your code. Prices and context windows below come from the live catalog.

ModelContextPrice / 1M tokens (in / out)Privacy
DeepSeek V4.1 Flash 1017deepseek-ai/DeepSeek-V4.1-Flash-10171.05M$0.3 / $1.2 outPrivate TEE
GLM 5.3 Flashz-ai/glm-5.3-flash1.05M$0.08 / $0.5 outPrivate TEE
Qwen 3.6 35B A3B FP8Qwen/Qwen3.6-35B-A3B-FP8262K$0.17 / $1.1 outPrivate TEE
Qwen 3.8 27BQwen/Qwen3.8-27B262K$0.04 / $1.35 outPrivate TEE
Qwen3-VL-30B-A3B-InstructQwen/Qwen3-VL-30B-A3B-Instruct16K$0.15 / $0.55 outPrivate TEE
deepseek-v3.2deepseek/deepseek-v3.2128K$1.1 / $1.1 outPrivate 3P TEE
GLM 5.3z-ai/glm-5.31.05M$1.8 / $5.75 outPrivate 3P TEE
Kimi K2.6moonshotai/kimi-k2.6262K$0.81 / $3.85 outPrivate 3P TEE

All 11 private models, with privacy tiers

  1. Create a NEAR AI Cloud account.Pay per token, no minimums.
  2. Create an API key.Use it with any OpenAI SDK.
  3. Verify, then build.Check the attestation in the Verification Center, then point your app at the API.
bash · OpenAI-compatible
curl https://cloud-api.near.ai/v1/chat/completions \
  -H "Authorization: Bearer $NEARAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017",
    "messages": [{"role": "user", "content": "Summarize this contract clause."}]
  }'
FAQ

Questions people ask about private AI.

What is private AI?

Private AI is AI that does not expose your data to anyone else while it works. It means running a model on your own hardware, or using a private inference API that runs the model inside sealed hardware (a TEE) and lets you verify that nobody else can read your prompts.

Is ChatGPT encrypted?

In transit and at rest, yes. OpenAI says your content is encrypted between you and OpenAI and when it is stored. It is not end-to-end encrypted: OpenAI holds the keys, so its systems process your conversations in readable form.

Is ChatGPT private?

Not in the sense of private inference. Your conversations are readable on OpenAI's systems. On the Free, Plus and Pro plans, OpenAI says it may use your content to train its models unless you turn off "Improve the model for everyone". Business plans are not used for training by default.

What is the difference between private AI and ChatGPT?

With ChatGPT you trust OpenAI's policies about who can read your conversations. With private AI inference, the model runs in hardware the provider cannot see into, and you can verify it with a hardware attestation. Private inference runs open-weight models, so the models differ too.

What is a trusted execution environment (TEE)?

A TEE is an area of a processor that keeps code and data isolated and encrypted from the rest of the machine, including its operating system and operator. NEAR AI Cloud uses Intel TDX on the CPU and NVIDIA confidential computing on the GPU.

What is confidential AI?

Confidential AI is AI that runs on confidential computing hardware, so data stays encrypted while it is being processed, not only in transit and at rest. Private AI inference is confidential AI applied to running models.

How do I verify that inference is private?

Ask the service for an attestation report, check its signatures against Intel's and NVIDIA's attestation services, and compare its code measurement with the published source. NEAR AI Cloud has a browser Verification Center and open-source verifiers that do these checks.

Is private AI inference slower?

Slightly. Confidential computing adds encryption work. NVIDIA's confidential computing mode runs on the GPU itself, and NEAR AI's documentation describes the latency overhead as minimal. Test your own workload to measure the difference.

Can I use private AI inference with the OpenAI SDK?

Yes. NEAR AI Cloud has an OpenAI-compatible API, so you change the base URL and API key and keep your code.

Are all NEAR AI Cloud models private?

No. Models marked Private TEE run in NEAR AI's own enclaves, and models marked Private 3P TEE run in a third party's attested enclave. Other models are marked Incognito: NEAR AI hides your account from the provider, but there is no hardware privacy guarantee. Each model page shows its tier.

Private by hardware. Proven by attestation.

Open-weight models in TEEs, through an OpenAI-compatible API, on NEAR AI Cloud.