Skip to content

Commit 6e0ae32

Browse files
Merge pull request #3 from nearai/fix/address-feedback
fix: implement feedback
2 parents 48f9561 + 82779c3 commit 6e0ae32

File tree

8 files changed

+365
-76
lines changed

8 files changed

+365
-76
lines changed

docs/cloud/models.mdx

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ import QwenIcon from '@site/static/img/icons/models/Qwen_logo.svg';
1212
import ZaiIcon from '@site/static/img/icons/models/zai-logo.svg';
1313
import CodeBlock from '@theme/CodeBlock';
1414

15-
NEAR AI Cloud provides access to leading AI models, each optimized for different use cases from advanced reasoning and tool calling to long-context processing and multilingual tasks. All models run in secure TEE environments with transparent, pay-per-use pricing.
15+
NEAR AI Cloud provides access to leading AI models, each optimized for different use cases ranging from advanced reasoning and tool calling to long-context processing and multilingual tasks. All models run in secure TEE environments with transparent, pay-per-use pricing.
1616

1717
## Quick Reference
1818

@@ -27,6 +27,13 @@ NEAR AI Cloud provides access to leading AI models, each optimized for different
2727
</tr>
2828
</thead>
2929
<tbody>
30+
<tr>
31+
<td><CodeBlock language="text">zai-org/GLM-4.6-FP8</CodeBlock></td>
32+
<td>200K</td>
33+
<td>$1.20/M</td>
34+
<td>$3.60/M</td>
35+
<td>Agentic applications, advanced coding, tool use, refined writing</td>
36+
</tr>
3037
<tr>
3138
<td><CodeBlock language="text">deepseek-ai/DeepSeek-V3.1</CodeBlock></td>
3239
<td>128K</td>
@@ -48,13 +55,6 @@ NEAR AI Cloud provides access to leading AI models, each optimized for different
4855
<td>$0.45/M</td>
4956
<td>Ultra-long context (262K), reasoning, instruction following, multilingual</td>
5057
</tr>
51-
<tr>
52-
<td><CodeBlock language="text">zai-org/GLM-4.6-FP8</CodeBlock></td>
53-
<td>200K</td>
54-
<td>$0.75/M</td>
55-
<td>$2.00/M</td>
56-
<td>Agentic applications, advanced coding, tool use, refined writing</td>
57-
</tr>
5858
</tbody>
5959
</table>
6060

docs/cloud/private-inference.mdx

Lines changed: 16 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -13,17 +13,17 @@ import { FeatureCard, FeatureCardGrid } from '@site/src/components/FeatureCard';
1313

1414
# Private Inference
1515

16-
When you use traditional AI services, your data passes through systems controlled by cloud providers and AI companies. Your prompts, the AI's responses, and even the processing of your requests are all visible to these third parties. This creates serious privacy concerns for sensitive applications.
16+
When you use traditional AI services, your data passes through systems controlled by cloud providers and AI companies. Your prompts, the AI's responses, and even the processing of your requests are all visible to these third parties. This creates serious security concerns for sensitive applications.
1717

18-
**Private inference solves this problem.** It ensures that AI computations happen in a completely isolated environment where no one—not the cloud provider, not the model provider, not even NEARcan access your data. At the same time, you can independently verify that your requests were actually processed in this secure environment through cryptographic attestation.
18+
**Private inference solves this problem.** It ensures that AI computations happen in a completely isolated environment where no one—not the cloud provider, not the model provider, not even NEAR AI can access your data. At the same time, you can independently verify that your requests were actually processed in this secure environment through cryptographic attestation.
1919

2020
This guide explains how NEAR AI Cloud implements private inference using Trusted Execution Environments (TEEs), the architecture that protects your data, and the security guarantees you can rely on.
2121

2222
---
2323

2424
## What is Private Inference?
2525

26-
Private inference is a method of running AI models where both your input data and the model's outputs remain completely hidden from everyone except you—even while the computation happens on remote servers you don't control.
26+
Private inference is a method of running AI models where both your input data and the model's outputs remain completely hidden from everyone except the user and client even while the computation happens on remote servers you don't control.
2727

2828
Traditional cloud AI services require you to trust that providers won't access your data. Private inference eliminates this need for trust by using hardware-based security that makes it technically impossible for anyone to see your data, even with physical access to the servers.
2929

@@ -56,7 +56,7 @@ NEAR AI Cloud's private inference provides three core guarantees:
5656
</div>
5757
<div className="feature-highlight-content">
5858
<h3>Production Performance</h3>
59-
<p>Hardware-accelerated TEEs with NVIDIA H200 GPUs deliver high-throughput inference with minimal latency overhead, making private inference practical for real-world applications.</p>
59+
<p>Hardware-accelerated TEEs with <a href="https://www.nvidia.com/en-us/data-center/solutions/confidential-computing/" target="_blank">NVIDIA Confidential Computing</a> deliver high-throughput inference with minimal latency overhead, making private inference practical for real-world applications.</p>
6060
</div>
6161
</div>
6262
</div>
@@ -69,13 +69,13 @@ NEAR AI Cloud's private inference provides three core guarantees:
6969

7070
NEAR AI Cloud combines Intel TDX and NVIDIA TEE technologies to create isolated, secure environments for AI computation:
7171

72-
- **Intel TDX (Trust Domain Extensions)**
72+
- **[Intel TDX(Trust Domain Extensions)](https://www.intel.com/content/www/us/en/developer/tools/trust-domain-extensions/overview.html)** :
7373
Creates confidential virtual machines (CVMs) that isolate your AI workloads from the host system, preventing unauthorized access to data in memory.
7474

75-
- **NVIDIA TEE**
75+
- **[NVIDIA TEE](https://www.nvidia.com/en-us/data-center/solutions/confidential-computing/)** :
7676
Provides GPU-level isolation for model inference, ensuring model weights and computations remain completely private during processing.
7777

78-
- **Cryptographic Attestation**
78+
- **[Cryptographic Attestation](/cloud/verification)** :
7979
Each TEE environment generates cryptographic proofs of its integrity and configuration, enabling independent verification of the secure execution environment.
8080

8181
### The Inference Process
@@ -104,26 +104,7 @@ When you make a request to NEAR AI Cloud, your data flows through a secure pipel
104104

105105
## Architecture Overview
106106

107-
NEAR AI Cloud operates through a distributed architecture consisting of an LLM Gateway and a network of Private LLM Nodes:
108-
109-
```
110-
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
111-
│ Private LLM │ │ Private LLM │ │ Private LLM │
112-
│ (8x H200) │ │ (8x H200) │ │ (8x H200) │
113-
├─────────────────┤ ├─────────────────┤ ├─────────────────┤
114-
│ Intel TDX CVM │ │ Intel TDX CVM │ │ Intel TDX CVM │
115-
│ NVIDIA TEE │ │ NVIDIA TEE │ │ NVIDIA TEE │
116-
│ Private-ML-SDK │ │ Private-ML-SDK │ │ Private-ML-SDK │
117-
└─────────────────┘ └─────────────────┘ └─────────────────┘
118-
│ │ │
119-
└───────────────────────┼───────────────────────┘
120-
121-
┌─────────────────┐
122-
│ LLM Gateway │
123-
│ Key Creation │
124-
│ Usage Tracking │
125-
└─────────────────┘
126-
```
107+
NEAR AI Cloud operates through a distributed architecture consisting of an LLM Gateway and a network of Private LLM Nodes.
127108

128109
### Private LLM Nodes
129110

@@ -151,32 +132,32 @@ The LLM Gateway serves as the central orchestration layer:
151132

152133
NEAR AI Cloud's private inference implements multiple layers of security to protect your data:
153134

154-
- **Hardware-Level Isolation**
135+
- **Hardware-Level Isolation** :
155136
TEEs create isolated execution environments enforced at the hardware level, preventing unauthorized access to memory and computation even from privileged system administrators or cloud providers.
156137

157-
- **Secure Communication**
138+
- **Secure Communication** :
158139
All communication between your applications and the LLM infrastructure uses end-to-end encryption, protecting data in transit from network-level attacks.
159140

160-
- **Cryptographic Attestation**
141+
- **Cryptographic Attestation** :
161142
Every TEE environment generates cryptographic proofs that verify the integrity of the execution environment, allowing you to independently confirm your computations occurred in a genuine, unmodified TEE.
162143

163-
- **Result Authentication**
144+
- **Result Authentication** :
164145
All AI outputs are cryptographically signed inside the TEE before leaving the secure environment, ensuring the authenticity and integrity of responses.
165146

166147
### Threat Protection
167148

168149
NEAR AI Cloud's architecture protects against common attack vectors:
169150

170-
- **Malicious Infrastructure Providers**
151+
- **Malicious Infrastructure Providers** :
171152
Hardware-enforced TEE isolation prevents cloud infrastructure providers from accessing your prompts, model weights, or inference results, even with physical access to servers.
172153

173-
- **Network-Based Attacks**
154+
- **Network-Based Attacks** :
174155
End-to-end encryption protects your data during transmission, preventing man-in-the-middle attacks and network eavesdropping.
175156

176-
- **Model Extraction Attempts**
157+
- **Model Extraction Attempts** :
177158
Model weights remain encrypted and isolated within the TEE, making extraction computationally infeasible even for attackers with privileged system access.
178159

179-
**Result Tampering**
160+
**Result Tampering** :
180161
Cryptographic signatures generated inside the TEE ensure that responses cannot be modified in transit without detection, maintaining the integrity of AI outputs.
181162

182163
---

docs/cloud/quickstart.mdx

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -20,8 +20,8 @@ import { FeatureCard, FeatureCardGrid } from '@site/src/components/FeatureCard';
2020
## Setup
2121

2222
1) **Create your account** - Sign up at [cloud.near.ai](https://cloud.near.ai/)
23-
2) **Add Credits** - Goto the "Credits" section and purchase credits based on your needs
24-
3) **Generate API Key** - Goto the "API Keys" section and generate a new key
23+
2) **Add Credits** - Go to the "Credits" section and purchase credits based on your needs
24+
3) **Generate API Key** - Go to the "API Keys" section and generate a new key
2525

2626
:::tip Keep Your API Key Safe
2727
Never share your API key publicly or commit it to version control. If compromised, you can regenerate it anytime from your dashboard.

docs/cloud/verification/index.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ import ModelsIcon from '@site/static/img/icons/models-icon.svg';
1010
import ChatIcon from '@site/static/img/icons/chat.svg';
1111
import { FeatureCard, FeatureCardGrid } from '@site/src/components/FeatureCard';
1212

13-
[NEAR AI Cloud](https://cloud.near.ai) operates in Trusted Execution Environments (TEEs) which use cryptographic proofs to verify that your private AI conversations actually happened in secure, isolated environments - not on compromised systems or with unauthorized access.
13+
[NEAR AI Cloud](https://cloud.near.ai) operates in Trusted Execution Environments (TEEs) which use cryptographic proofs to verify that your private AI conversations actually happened in secure, isolated environments that are not on compromised systems or with unauthorized access.
1414

1515
This section will show you step-by-step processes for checking these proofs, validating digital signatures, and confirming that your AI interactions haven't been tampered with.
1616

docs/index.mdx

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
id: index
3+
title: NEAR AI Cloud - Private, Verifiable AI Platform
4+
sidebar_label: Home
5+
slug: /
6+
description: Deploy and scale powerful language models on TEE-enabled GPUs with on-chain guarantees. Fully private, verifiable, and user-owned AI platform.
7+
hide_title: true
8+
displayed_sidebar: docsSidebar
9+
---
10+
11+
import HomePageContent from '@site/src/components/HomePageContent';
12+
13+
<HomePageContent />
Lines changed: 10 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,12 @@
11
import clsx from "clsx";
22
import Link from "@docusaurus/Link";
3-
import useDocusaurusContext from "@docusaurus/useDocusaurusContext";
4-
import Layout from "@theme/Layout";
5-
import HomepageFeatures from "@site/src/components/HomepageFeatures";
6-
73
import Heading from "@theme/Heading";
8-
import styles from "./index.module.css";
9-
import VerifiedGif from "@site/static/img/verified.gif";
4+
import styles from "./styles.module.css";
105
import PrivateInferenceIcon from "@site/static/img/icons/private-inference.svg";
116
import VerificationIcon from "@site/static/img/icons/verification.svg";
127
import QuickstartIcon from "@site/static/img/icons/quickstart.svg";
138

149
function HomepageHeader() {
15-
const { siteConfig } = useDocusaurusContext();
1610
return (
1711
<header className={clsx("hero hero--primary", styles.heroBanner)}>
1812
<div className="container">
@@ -30,36 +24,33 @@ function HomepageHeader() {
3024
<div className={styles.buttons}>
3125
<Link
3226
className="button button--secondary button--lg"
33-
to="/cloud/quickstart"
27+
to="/cloud/introduction"
3428
>
35-
Start Building
29+
Get Started
3630
</Link>
3731
</div>
3832
</div>
3933
</header>
4034
);
4135
}
4236

43-
export default function Home() {
44-
const { siteConfig } = useDocusaurusContext();
37+
export default function HomePageContent() {
4538
return (
46-
<Layout
47-
title="NEAR AI Cloud - Private, Verifiable AI Platform"
48-
description="Deploy and scale powerful language models on TEE-enabled GPUs with on-chain guarantees. Fully private, verifiable, and user-owned AI platform."
49-
>
39+
<>
5040
<HomepageHeader />
5141
<main>
5242
<div className="container margin-vert--lg">
5343
<div className="row">
54-
<div className="col col--8 col--offset-2">
44+
<div className="col">
5545
<div className="markdown">
5646
<div className={styles.lead}>
5747
<p className={styles.leadCopy}>
5848
NEAR AI runs the models you trust in secure Trusted
5949
Execution Environments (TEEs), ensuring your data stays
6050
completely private. Model providers, cloud providers, and
61-
NEAR cannot access, view, or use your data for training —
62-
your information remains yours alone.
51+
NEAR AI cannot access, view, or use your data for training.
52+
<br />
53+
<center><strong>Your information remains yours.</strong></center>
6354
</p>
6455
</div>
6556
<div className={clsx("row", styles.featureRow)}>
@@ -134,6 +125,6 @@ export default function Home() {
134125
</div>
135126
</div>
136127
</main>
137-
</Layout>
128+
</>
138129
);
139130
}

0 commit comments

Comments
 (0)