# Table of Contents - [Meet Gradient | Gradient](#meet-gradient-gradient) - [Parallax | Gradient](#parallax-gradient) - [API Reference Documentation | Gradient](#api-reference-documentation-gradient) - [User Experiences | Gradient](#user-experiences-gradient) - [The Open Intelligence Stack | Gradient](#the-open-intelligence-stack-gradient) - [Gradient Cloud | Gradient](#gradient-cloud-gradient) - [Sentry Node Open Beta (Concluded) | Gradient](#sentry-node-open-beta-concluded-gradient) - [Sentry Nodes User Guide (Legacy) | Gradient](#sentry-nodes-user-guide-legacy-gradient) - [Rewards (Concluded) | Gradient](#rewards-concluded-gradient) - [Community Guidelines | Gradient](#community-guidelines-gradient) - [Seasons | Gradient](#seasons-gradient) - [Account Boosts | Gradient](#account-boosts-gradient) - [Referral Bonus | Gradient](#referral-bonus-gradient) - [Official Links | Gradient](#official-links-gradient) - [FAQ | Gradient](#faq-gradient) - [Parallax | Gradient](#parallax-gradient) - [Parallax | Gradient](#parallax-gradient) - [Echo | Gradient](#echo-gradient) - [Gradient Cloud | Gradient](#gradient-cloud-gradient) - [Lattica | Gradient](#lattica-gradient) - [User Experiences | Gradient](#user-experiences-gradient) - [Edge Host Pilot Program | Gradient](#edge-host-pilot-program-gradient) - [FAQ | Gradient](#faq-gradient) --- # Meet Gradient | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Gradient is an AI R&D lab dedicated to building **open intelligence** through a fully decentralized infrastructure — **OIS (Open Intelligence Stack)**, encompassing **distributed training, serving,** agentic systems, and more. We are solving the hardest and most ambitious problem in the intersection of Blockchain x AI: How do we train/serve good LLMs over public internet — Is it even possible to build an OpenAI competitor over a permissionless, autonomous network? Our current OIS includes **Parallax** for distributed serving, **Echo** for distributed reinforcement learning, and **Gradient Cloud** for enterprise solutions. Backed by **top investors** and a team of **world-class researchers**, Gradient is committed to releasing more frontier research that will unlock a future where **intelligence can be assembled, scaled, and evolved by anyone, anywhere**. ### [](https://docs.gradient.network/#our-mission) Our mission Gradient is building the world’s first Open Intelligence Stack: a sovereign, peer-powered infrastructure where intelligence is hosted, served, and owned by the people. Our goal is a global foundation that enables the **distribution, evolution, and embodiment** of intelligence. [NextThe Open Intelligence Stack](https://docs.gradient.network/the-open-intelligence-stack) Last updated 19 days ago --- # Parallax | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Parallax is the operating system for sovereign AI. Under the hood, it is a distributed runtime and service fabric that turns heterogeneous machines into one traceable service you can build on. When a model is too big for one host, it is sharded into contiguous layer slices and distributed across your laptop, a lab GPU, and a teammate’s workstation, all orchestrated as one service. Each request takes the fastest path on a single host, across a LAN, or over the public internet, without a public IP or matching hardware. Parallax opens up a wide range of ways to host and run your own AI apps and agents that are completely your own, including coding copilots, personal assistants, vision and speech pipelines, and multi-agent simulations. At launch, Parallax supports **40+ open models** from **0.6B** to **trillion-class MoE** on **GPUs** and **Apple Silicon**, across **Windows, Linux, and macOS**. * Host your own AI cluster: [github.com/GradientHQ/parallax](http://github.com/GradientHQ/parallax) [PreviousThe Open Intelligence Stack](https://docs.gradient.network/the-open-intelligence-stack) [NextGradient Cloud](https://docs.gradient.network/enterprise-solutions/gradient-cloud) Last updated 19 days ago --- # API Reference Documentation | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#overview) Overview ------------------------------------------------------------------------------------------------------------------------ Our AI API implements OpenAI-compatible interfaces that support: * Model listing and querying * Chat completion (streaming and non-streaming) * Text completion (streaming and non-streaming) * Administrator model management [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#basic-information) Basic Information ------------------------------------------------------------------------------------------------------------------------------------------ * **Base URL**: `https://apis.gradient.network/api/v1` * **Authentication**: Access Key * **Content Type**: `application/json` * **API Version**: v1 [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#authentication) Authentication ------------------------------------------------------------------------------------------------------------------------------------ ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#access-key-authentication) Access Key Authentication Copy Authorization: Bearer your-access-key-here [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#api-endpoints) API Endpoints ---------------------------------------------------------------------------------------------------------------------------------- ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-1.-model-management-apis) 1\. Model Management APIs #### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-1.1-list-all-models) **1.1 List All Models** **Endpoint**: `GET /ai/models` **Description**: List of all available AI models (no authentication required) **Request Parameters**: None **Response Example**: Copy { "object": "list", "data": [\ {\ "id": "qwen/qwen3-coder-480b-instruct-fp8",\ "object": "model",\ "created": 1640995200,\ "owned_by": "qwen",\ "permission": [],\ "root": "qwen/qwen3-coder-480b-instruct-fp8",\ "parent": null\ }\ ] } **Error Codes**: * `200`: Success * `500`: Internal Server Error ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-2.-chat-completion-api) 2\. Chat Completion API #### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-2.1-chat-completion) **2.1 Chat Completion** **Endpoint**: `POST /ai/chat/completions` **Description**: Create a chat completion request, supporting both streaming and non-streaming responses **Authentication**: Access Key **Request Parameters**: Parameter Type Required Description `model` string Yes The ID of the model to use `messages` array Yes Array of conversation messages `stream` boolean No Whether to use streaming response, default false `max_tokens` integer No Maximum number of tokens to generate `temperature` number No Sampling temperature, 0-2, default 1 `top_p` number No Nucleus sampling parameter, 0-1, default 1 `n` integer No Number of responses to generate, default 1 `stop` string/array No Stop generation tokens `presence_penalty` number No Presence penalty, -2.0 to 2.0, default 0 `frequency_penalty` number No Frequency penalty, -2.0 to 2.0, default 0 `logit_bias` object No Modify sampling probability for specified tokens `user` string No User identifier **Request Example**: Copy { "model": "qwen/qwen3-coder-480b-instruct-fp8", "messages": [\ {\ "role": "user",\ "content": "Hello, how are you?"\ }\ ], "temperature": 0.7, "max_tokens": 100 } **Non-streaming Response Example**: Copy { "id": "chatcmpl-123", "object": "chat.completion", "created": 1677652288, "model": "qwen/qwen3-coder-480b-instruct-fp8", "choices": [\ {\ "index": 0,\ "message": {\ "role": "assistant",\ "content": "Hello! I'm doing well, thank you for asking. How can I help you today?"\ },\ "finish_reason": "stop"\ }\ ], "usage": { "prompt_tokens": 9, "completion_tokens": 12, "total_tokens": 21 } } **Streaming Response Example**: Copy data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"qwen/qwen3-coder-480b-instruct-fp8","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]} data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"qwen/qwen3-coder-480b-instruct-fp8","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]} data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"qwen/qwen3-coder-480b-instruct-fp8","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]} data: [DONE] **Error Codes**: * `200`: Success * `400`: Bad Request * `401`: Unauthorized * `402`: Billing Check Failed * `404`: Model Not Found * `429`: Rate Limit Exceeded * `500`: Internal Server Error ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-3.-text-completion-api) 3\. Text Completion API #### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-3.1-text-completion) **3.1 Text Completion** **Endpoint**: `POST /ai/completions` **Description**: Create a text completion request, supporting both streaming and non-streaming responses **Authentication**: Access Key **Request Parameters**: Parameter Type Required Description `model` string Yes The ID of the model to use `prompt` string/array Yes Prompt text `suffix` string No Suffix to append after inserted text `max_tokens` integer No Maximum number of tokens to generate `temperature` number No Sampling temperature, 0-2, default 1 `top_p` number No Nucleus sampling parameter, 0-1, default 1 `n` integer No Number of responses to generate, default 1 `stream` boolean No Whether to use streaming response, default false `logprobs` integer No Return log probabilities for most likely tokens `echo` boolean No Whether to echo the prompt, default false `stop` string/array No Stop generation tokens `presence_penalty` number No Presence penalty, -2.0 to 2.0, default 0 `frequency_penalty` number No Frequency penalty, -2.0 to 2.0, default 0 `best_of` integer No Select from best candidates, default 1 `logit_bias` object No Modify sampling probability for specified tokens `user` string No User identifier **Request Example**: Copy { "model": "qwen/qwen3-coder-480b-instruct-fp8", "prompt": "Complete this sentence: The quick brown fox", "max_tokens": 20, "temperature": 0.5 } **Response Example**: Copy { "id": "cmpl-123", "object": "text_completion", "created": 1677652288, "model": "qwen/qwen3-coder-480b-instruct-fp8", "choices": [\ {\ "text": " jumps over the lazy dog",\ "index": 0,\ "logprobs": null,\ "finish_reason": "stop"\ }\ ], "usage": { "prompt_tokens": 5, "completion_tokens": 7, "total_tokens": 12 } } **Error Codes**: * `200`: Success * `400`: Bad Request * `401`: Unauthorized * `402`: Billing Check Failed * `404`: Model Not Found * `429`: Rate Limit Exceeded * `500`: Internal Server Error [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#error-code-details) Error Code Details -------------------------------------------------------------------------------------------------------------------------------------------- ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#common-error-codes) Common Error Codes Error Code HTTP Status Description Solution `400` 400 Bad Request Check request parameter format and required fields `401` 401 Unauthorized Provide valid Access Key or JWT Token `402` 402 Billing Check Failed Check account balance and billing status `403` 403 Forbidden Confirm user permissions and roles `404` 404 Resource Not Found Check if resource ID is correct `429` 429 Rate Limit Exceeded Reduce request frequency or contact administrator `500` 500 Internal Server Error Contact technical support ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#ai-specific-error-codes) AI-Specific Error Codes Error Code Description Solution `model_not_found` Specified model does not exist Check model ID or use `/ai/models` to get available models `model_not_supported` Model does not support requested functionality Check model capabilities or use other models `context_length_exceeded` Input exceeds model context length limit Reduce input length or use models supporting longer context `invalid_parameters` Parameter values are invalid Check parameter ranges and formats `billing_check_failed` Billing check failed Check account balance and billing configuration [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#usage-examples) Usage Examples ------------------------------------------------------------------------------------------------------------------------------------ ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#python-examples) Python Examples Copy import requests import json # Configuration API_BASE = "https://apis.gradient.network/api/v1" API_KEY = "your-access-key-here" # Chat completion request def chat_completion(prompt, model="qwen/qwen3-coder-480b-instruct-fp8"): headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = { "model": model, "messages": [{"role": "user", "content": prompt}], "temperature": 0.7, "max_tokens": 100 } response = requests.post( f"{API_BASE}/ai/chat/completions", headers=headers, json=data ) return response.json() # Usage example result = chat_completion("Hello, how are you?") print(result) ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#javascript-examples) JavaScript Examples Copy // Configuration const API_BASE = "https://apis.gradient.network/api/v1"; const API_KEY = "your-access-key-here"; // Chat completion request async function chatCompletion(prompt, model = "qwen/qwen3-coder-480b-instruct-fp8") { const response = await fetch(`${API_BASE}/ai/chat/completions`, { method: 'POST', headers: { 'Authorization': `Bearer ${API_KEY}`, 'Content-Type': 'application/json' }, body: JSON.stringify({ model: model, messages: [{ role: 'user', content: prompt }], temperature: 0.7, max_tokens: 100 }) }); return await response.json(); } // Usage example chatCompletion("Hello, how are you?") .then(result => console.log(result)) .catch(error => console.error(error)); ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#curl-examples) cURL Examples Copy # Chat completion curl -X POST "https://apis.gradient.network/api/v1/ai/chat/completions" \ -H "Authorization: Bearer your-access-key-here" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen/qwen3-coder-480b-instruct-fp8", "messages": [{"role": "user", "content": "Hello, how are you?"}], "temperature": 0.7, "max_tokens": 100 }' # Get model list curl "https://apis.gradient.network/api/v1/ai/models" [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#rate-limits-and-quotas) Rate Limits and Quotas ---------------------------------------------------------------------------------------------------------------------------------------------------- ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#rate-limits) Rate Limits * **Free Users**: 60 requests per minute * **Paid Users**: Based on plan, typically 1000-10000 requests per minute ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#token-limits) Token Limits * **Input Tokens**: Based on model context length limits * **Output Tokens**: Based on model capabilities and billing limits ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#concurrency-limits) Concurrency Limits * **Free Users**: Maximum 3 concurrent requests * **Paid Users**: Based on plan, typically 10-100 concurrent requests [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#best-practices) Best Practices ------------------------------------------------------------------------------------------------------------------------------------ ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-1.-error-handling) 1\. Error Handling Copy try: response = chat_completion(prompt) if response.get('error'): print(f"Error: {response['error']['message']}") else: print(response['choices'][0]['message']['content']) except requests.exceptions.RequestException as e: print(f"Request failed: {e}") ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-2.-streaming-processing) 2\. Streaming Processing Copy def stream_chat_completion(prompt, model): headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } data = { "model": model, "messages": [{"role": "user", "content": prompt}], "stream": True } response = requests.post( f"{API_BASE}/ai/chat/completions", headers=headers, json=data, stream=True ) for line in response.iter_lines(): if line: line = line.decode('utf-8') if line.startswith('data: '): data = line[6:] # Remove 'data: ' prefix if data == '[DONE]': break try: json_data = json.loads(data) content = json_data['choices'][0]['delta'].get('content', '') if content: print(content, end='', flush=True) except json.JSONDecodeError: continue ### [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#id-3.-retry-mechanism) 3\. Retry Mechanism Copy import time from requests.adapters import HTTPAdapter from requests.packages.urllib3.util.retry import Retry def create_session_with_retry(): session = requests.Session() retry_strategy = Retry( total=3, backoff_factor=1, status_forcelist=[429, 500, 502, 503, 504] ) adapter = HTTPAdapter(max_retries=retry_strategy) session.mount("http://", adapter) session.mount("https://", adapter) return session # Use retry session session = create_session_with_retry() response = session.post(url, headers=headers, json=data) [](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation#support) Support ---------------------------------------------------------------------------------------------------------------------- If you encounter issues during usage, please: 1. Review the error code descriptions in this document 2. Check request parameters and authentication information 3. Contact the technical support team 4. Check the system status page **Technical Support Email**: support@your-domain.com **API Status Page**: https://status.your-domain.com [PreviousGradient Cloud](https://docs.gradient.network/enterprise-solutions/gradient-cloud) [NextUser Experiences](https://docs.gradient.network/user-products/user-experiences) Last updated 2 months ago --- # User Experiences | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) There are many ways to experience Gradient technology with the following products, tailor-made for general users. ![Cover](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FHOpaWebTeSR703sw0kpu%252F120b.png%3Falt%3Dmedia%26token%3D9b606ee8-a725-42aa-ae60-c945f35d3620&width=490&dpr=4&quality=100&sign=e0f86a69&sv=2) [**Gradient Chatbot**](https://chat.gradient.network/) Distributed inference with top LLMs, powered by Parallax. ![Cover](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FzWVkZHonFFSlcrRr0pRC%252FGtzT_rtbQAArwBn%2520%281%29.jpeg%3Falt%3Dmedia%26token%3D647a9f70-2777-4867-b3af-d73e77117914&width=490&dpr=4&quality=100&sign=14a2fb54&sv=2) [**Gradient Explorer**](https://explorer.gradient.network/) Glance through network stats and experience Lattica with distributed video streaming [PreviousAPI Reference Documentation](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) [NextSentry Node Open Beta (Concluded)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded) Last updated 2 months ago --- # The Open Intelligence Stack | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FvUHkDpDXnQFCtZfygKDD%252Fimage.png%3Falt%3Dmedia%26token%3D9d61419e-bb7a-4d51-8184-30ea98876eb2&width=768&dpr=4&quality=100&sign=9a69bea0&sv=2) ### [](https://docs.gradient.network/the-open-intelligence-stack#available-research) Available Research [Echo](https://docs.gradient.network/the-open-intelligence-stack/echo) [Lattica](https://docs.gradient.network/the-open-intelligence-stack/lattica) [Parallax](https://docs.gradient.network/the-open-intelligence-stack/parallax) [PreviousMeet Gradient](https://docs.gradient.network/) [NextParallax](https://docs.gradient.network/open-source/parallax) Last updated 19 days ago --- # Gradient Cloud | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) [Gradient Cloud](https://cloud.gradient.network/) is the all-in-one station for building with AI, powered by the Gradient distributed AI stack. Powered by Lattica, Parallax, and Echo, workloads are deployed and routed across a global network of hardware instead of centralized clusters. That’s how we unlock high throughput + low latency intelligence at low cost. Phase 1 is live with: • **Inference Endpoints** for leading open-source models • **Interactive Playground** with tunable params + one-click deploy All new accounts will be credited with a few million free tokens to jumpstart your AI ideas. You can find API details below: [API Reference Documentation](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) [PreviousParallax](https://docs.gradient.network/open-source/parallax) [NextAPI Reference Documentation](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) Last updated 2 months ago --- # Sentry Node Open Beta (Concluded) | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Status: Concluded The Gradient journey began with the **Sentry Node Open Beta**. The Gradient community’s incredible energy around the Sentry Node Open Beta has brought the network to life. What began as an exploratory initiative has grown into a living foundation powered by thousands of people worldwide. With millions of participants and billions of Taps, we have established a strong peer-to-peer connectivity foundation. Together, these Sentry Nodes form Lattica, our distributed data communication protocol. Season 1 has concluded on 28 August 2025, 12:00 UTC, marking the graduation of the Sentry Node Open Beta. Sentry Nodes will no longer accumulate new Uptime or Taps after that. For our community, this is not the end of participation—it is the beginning of the main act. #### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded#where-to-contribute-now) Where to contribute now * **Run a Host:** Join the [Edge Host Pilot Program](https://docs.gradient.network/user-products/edge-host-pilot-program) to provide compute capacity. * **Experiment with APIs:** Start building on [Gradient Cloud](https://docs.gradient.network/enterprise-solutions/gradient-cloud) . * **Follow Research:** Read our published papers on Parallax and Echo, and try open-sourced models on our [Hugging Face Collection](https://huggingface.co/Gradientresearch) . * Join the conversation and help us grow the [Discord](https://discord.gg/gradientnetwork) community. * Follow our [X page](https://x.com/Gradient_HQ) and stay tuned for more exciting ways to participate coming soon. [PreviousUser Experiences](https://docs.gradient.network/user-products/user-experiences) [NextSentry Nodes User Guide (Legacy)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy) Last updated 2 months ago --- # Sentry Nodes User Guide (Legacy) | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) The Sentry Node Open Beta has graduated. Season 0 and Season 1 are concluded. Sentry Nodes do not receive rewards at the current moment. This section is for reference only. Sentry Nodes are privacy-preserving, lightweight (<1MB data usage per month), and efficient Chrome Extensions with intermittent liveliness. They map global connectivity and play an important role Lattica — the data communication protocol. [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#get-a-sentry-node) Get a Sentry Node ------------------------------------------------------------------------------------------------------------------------------------------------------- 1 Sign up on [gradient.network](https://gradient.network/) . 2 Connect your X account and follow our official X account [@Gradient\_HQ](https://twitter.com/Gradient_HQ) . 3 Follow the instructions to download Sentry Node from the Chrome Web Store. [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#know-your-sentry-node) Know your Sentry Node --------------------------------------------------------------------------------------------------------------------------------------------------------------- ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#taps) Taps Peer-to-Peer connections are established periodically between two random, arbitrary Sentry Nodes to verify their connectivity. These ephemeral connections are called "Taps". A Tap is successful when a Peer-to-Peer connection is successfully established. The success rate of Taps depends on a range of network factors, such as your NAT type. ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#rewards) **Rewards** There are multiple ways to get rewards while contributing to Gradient’s pervasive global networking infrastructure. In Season 1, Sentry Nodes will get: * **Uptime Rewards** **(will be phased out later in the season)** * **Tap Rewards (with a daily cap)** * [**Referral Bonuses**](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/referral-bonus) * [**Account Boosts**](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/account-boosts) ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#node-status) **Node Status** * **Good:** The node is successfully connected to the server. * **Disconnected:** The node is offline. Please check your internet connection. * **Unsupported:** Your location may be unsupported, or your IP address is unsupported (Proxies, Data Center IPs, IPv6 addresses, IPs with fraudulent risk, etc.) * **Suspended:** The node is temporarily suspended due to unusual activities. Please refer to our [Community Guidelines](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines) for more details. [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#manage-your-sentry-node) Manage your Sentry Node ------------------------------------------------------------------------------------------------------------------------------------------------------------------- The [Gradient Dashboard](https://app.gradient.network/) is your all-in-one terminal for tracking, managing, and optimizing nodes and rewards on the Gradient Network. It offers intuitive visualizations of key account stats, including node status, different types of rewards, and referral activity. In addition, you can also update your profile to make the Gradient experience a truly personal one. You can track real-time node activity with key metrics like uptime and taps received, and data transmitted and use these insights to fine-tune your nodes for optimal performance. Rewards are organized into categories—Network, Boosts, and Referrals—so you can easily see how each activity impacts your earnings. As you advance through account tiers, you'll unlock additional boosts, increasing your reward potential. The referral system allows you to generate and share personal referral codes, and follow up on your referrals. [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#dos-and-donts) Dos and Don'ts ------------------------------------------------------------------------------------------------------------------------------------------------ Gradient Network is dedicated to building a network where users can benefit from its **long-term, sustainable growth**. To protect the interests of genuine users, we are committed to implementing the **strictest measures** against harmful actions and fostering a transparent, equitable ecosystem. ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#how-sentry-nodes-are-designed-to-work) How Sentry Nodes are designed to work: • Run on personal devices with minimal resource impact • No 24/7 attention needed • Generate valuable insights into our global network infrastructure. ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy#what-not-to-do) What not to do: Batch account creation, running multiple Sentry Nodes on the same device, using scripts or third-party tools, or other actions that violate our [Community Guidelines](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines) will result in account restrictions. Please check relevant guidelines regularly and use your Sentry Node in intended ways. [PreviousSentry Node Open Beta (Concluded)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded) [NextRewards (Concluded)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded) Last updated 2 months ago --- # Rewards (Concluded) | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) The Sentry Node Open Beta has graduated. Season 0 and Season 1 are concluded. Sentry Nodes do not receive rewards at the current moment. This section is for reference only. [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded#sentry-node-rewards) Sentry Node Rewards ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- There are multiple ways to get rewards while contributing to Gradient’s decentralized compute infrastructure. You can: * **Get Uptime Rewards by staying online. (to be phased out soon)** * **Get Tap Rewards for making successful "Taps".** * Taps are peer-to-peer connections established periodically between two random, arbitrary Sentry Nodes to verify their connectivity. * The success rate of Taps depends on a range of network factors, such as your NAT type. * **Get** [**Referral Bonuses**](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/referral-bonus) **with your referrals;** * [**Boost**](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/account-boosts) **your rewards by completing achievements.** [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded#seasons) Seasons ----------------------------------------------------------------------------------------------------------------------------------------------------- Seasons represent distinct periods of reward distribution. New seasons will be introduced alongside future milestones. Reward schedules may vary between seasons, and points are non-fungible across seasons. The current Season is [**Season 1**](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/seasons/season-1) . [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded#community-guidelines) Community Guidelines ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Gradient Network encourages genuine participation that supports the platform's growth in the long term. We are actively taking actions against Sybil and other harmful behaviors. Please refer to our [**Community Guidelines**](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded#community-guidelines) or the updated DOs and DON'Ts on Sentry Nodes. [PreviousSentry Nodes User Guide (Legacy)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy) [NextSeasons](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/seasons) Last updated 2 months ago --- # Community Guidelines | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Thank you for being part of the #GradientSentry community! Gradient Network is dedicated to building a network where users can benefit from its **long-term, sustainable growth**. We value fair and honest participation, as this is the only way to achieve that goal. To protect the interests of genuine users, we are committed to implementing the **strictest measures** against harmful actions and fostering a transparent, equitable ecosystem. Our team is constantly optimizing our methods to identify behaviors that may be harmful to our ecosystem and users. Please be advised that the team reserves the right to **retrospectively slash points** earned through Sybil or fraudulent activities. These guidelines will be updated periodically, so please check this page regularly for the latest version. ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines#id-1.-each-user-should-register-for-only-one-account) 1\. Each user should register for only one account. ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252Fsw2boJaUmNK0FJGn1dj7%252FFrame%25202072750696%2520%281%29.png%3Falt%3Dmedia%26token%3D4f4f8efa-7c16-4f9d-a747-62e42c6713c5&width=768&dpr=4&quality=100&sign=59f93741&sv=2) ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines#id-2.-install-only-one-sentry-node-on-each-device) 2\. Install only one Sentry Node on each device. ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FX8tEWiBTrvzqkEX3XtV5%252FFrame%25202072750697.png%3Falt%3Dmedia%26token%3Ddf08af00-e2e0-45b8-8e8d-2d2a10fece43&width=768&dpr=4&quality=100&sign=ee35b572&sv=2) ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines#id-3.-rules-on-multiple-sentry-nodes) 3\. Rules on multiple Sentry Nodes. Users can have multiple Sentry Nodes, as long as other rules are met. However, rewards will be split between Sentry Nodes having the same IP address. ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FBgQAYFstlXk7Z8ICD7vy%252FFrame%25202072750698.png%3Falt%3Dmedia%26token%3D8a2662d0-aaa8-4c9d-b317-75adfa9d4528&width=768&dpr=4&quality=100&sign=51eac9aa&sv=2) ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines#id-4.-certain-ip-types-are-not-supported-by-the-network) 4\. Certain IP types are not supported by the network. Sentry Nodes with an “Unsupported” status will stop receiving rewards. Rewards will resume accumulating once the status changes to “Good”. ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FXDZT8iybXQHO54DdzesN%252FFrame%25202072750699.png%3Falt%3Dmedia%26token%3D0591c2c2-fd8c-4bff-a5a4-1f8ae1209ced&width=768&dpr=4&quality=100&sign=bdc601ee&sv=2) ### [](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines#id-5.-keep-your-sentry-node-updated) 5\. Keep your Sentry Node updated. Ensure you are always using the latest version of the Sentry Node. Certain features and rewards may not be available on older versions. * Check your current version: * Click your profile picture on your Sentry Node extension; * Click "About"; * Find your current version number after "Version:". * Update your Sentry Node: [Please refer to this section.](https://docs.gradient.network/hide/troubleshoot#id-1.-update-your-sentry-node) * Check the latest version number: [Visit the Chrome Web Store](https://chromewebstore.google.com/detail/gradient-sentry-node/) . [PreviousReferral Bonus](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/referral-bonus) [NextFAQ](https://docs.gradient.network/learn-more/faq) Last updated 11 months ago --- # Seasons | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) **Live: Season 1** Seasons represent distinct periods of reward distribution. New seasons will be introduced alongside future milestones. Reward schedules may vary, and points are non-fungible across seasons. Seasons Start Date End Date Season 1 **15th April 2025** Season 0 **12th September 2024** **14th April 2025** [PreviousRewards (Concluded)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded) [NextSeason 1](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/seasons/season-1) Last updated 7 months ago --- # Account Boosts | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Completing achievements allows users to gain experience (EXP), which helps elevate their account statuses. As users gain more EXP and unlock higher status levels, they will receive a higher reward boost that benefits all nodes associated with the account. Account Status Reward Boost Iron 0% Bronze 2% Silver 4% Gold 6% Platinum 8% Diamond 10% Reward Boost applies to Uptime and Tap rewards. NOT applicable to Referral Bonuses. [PreviousSeason 0](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/seasons/season-0) [NextReferral Bonus](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/referral-bonus) Last updated 7 months ago --- # Referral Bonus | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) The referral system allows users to get bonus rewards by expanding their referral network and engaging with it, all while contributing to the growth and success of the platform. There are 2 ways to get rewards from referrals: 1. One-time bonus: Both parties of a referral will get 20 points when your referee reaches 72 hours of uptime. 2. Perpetual bonus: Referrers will get a perpetual bonus of their primary and secondary referees' rewards： Primary Referral Secondary Referral When you refer a new user to contribute to the network, you will get a **10%** bonus for their Uptime and Tap rewards. When your primary referees refer other users (secondary referral), you will get an extra **5%** of Uptime and Tap rewards from your secondary referees. [PreviousAccount Boosts](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/account-boosts) [NextCommunity Guidelines](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines) Last updated 7 months ago --- # Official Links | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) **Scam Alert** We've received multiple reports of phishing emails impersonating Gradient. These emails may ask for donations or prompt you to interact with third-party URLs. These are **100% scams**. A closer look at the sender's address will easily reveal their true identity. - Do NOT interact with any unknown site. Check the URL letter by letter. - Do NOT respond to emails claiming to represent Gradient. - Gradient will NEVER ask for donations or request payments via email or DMs. - Trust only information from our official channels. * [Website](https://gradient.network/) * [X](https://x.com/Gradient_HQ) * [Discord](https://discord.com/invite/gradientnetwork) * [Gradient Chatbot](https://chat.gradient.network/) * [Gradient Explorer](https://explorer.gradient.network/) * [Gradient Cloud](https://cloud.gradient.network/) * [Hugging Face](https://huggingface.co/GradientResearch) * [Careers](https://careers.gradient.network/) [PreviousFAQ](https://docs.gradient.network/learn-more/faq) Last updated 2 months ago --- # FAQ | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) [](https://docs.gradient.network/learn-more/faq#general) General --------------------------------------------------------------------- #### [](https://docs.gradient.network/learn-more/faq#what-is-gradient-building) **What is Gradient building?** > Gradient is building the world’s first fully distributed AI stack — a peer-powered infrastructure where intelligence is hosted, served, and owned by the people. #### [](https://docs.gradient.network/learn-more/faq#what-makes-gradient-different) **What makes Gradient different?** > Instead of running models in closed datacenters, Gradient is distributing AI workloads across a global mesh of consumer devices and compatible datacenters. This reduces cost, improves resilience, and democratizes access. * * * ### [](https://docs.gradient.network/learn-more/faq#research) Research #### [](https://docs.gradient.network/learn-more/faq#what-has-gradient-done-in-the-field-of-distributed-ai) What has Gradient done in the field of distributed AI? > We have released research and products on: [Lattica](https://docs.gradient.network/the-open-intelligence-stack/lattica) > (peer-to-peer data communication) [Parallax](https://docs.gradient.network/the-open-intelligence-stack/parallax) > (distributed inference) [Echo](https://docs.gradient.network/the-open-intelligence-stack/echo) > (distributed reinformcement learning) More work on multi-agent collaboration, self-evolving agentic systems are more are in the pipeline. * * * ### [](https://docs.gradient.network/learn-more/faq#gradient-cloud) Gradient Cloud **What is Gradient Cloud?** > [Gradient Cloud](https://docs.gradient.network/enterprise-solutions/gradient-cloud) > is the dev-facing, one-stop solution to access Gradient's distributed AI stack. In phase 1, it's offering inference endpoints, APIs, and a Playground to build and deploy AI workloads. More features coming in phase 2. **Is Gradient Cloud compatible with OpenAI-style APIs?** > Yes. Core endpoints follow the same schema, with Gradient-native extensions for scheduling and privacy controls. **What models are available?** > Leading open-source LLMs, with more added continuously. Model IDs are published in the [API Reference](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) > . #### [](https://docs.gradient.network/learn-more/faq#sentry-nodes) Sentry Nodes **Is the Sentry Node Open Beta still active?** > No. The Open Beta has concluded and Sentry Nodes are no longer accumulating new Uptime or Taps rewards. The sections on Sentry Nodes within this documentation is for reference purposes only. * * * ### [](https://docs.gradient.network/learn-more/faq#whats-next) **What’s next** > The team is constantly cooking. Stay tuned for more seamless, tangible experience, where every community member will gain direct access to the full power of distributed intelligence. **Scam Alert** We've received multiple reports of phishing emails impersonating Gradient. These emails may ask for donations or prompt you to interact with third-party URLs. These are **100% scams**. A closer look at the sender's address will easily reveal their true identity. - Do NOT interact with any unknown site. Check the URL letter by letter. - Do NOT respond to emails claiming to represent Gradient. - Gradient will NEVER ask for donations or request payments via email or DMs. - Trust only information from our official channels. ### [](https://docs.gradient.network/learn-more/faq#where-can-i-get-real-time-updates-from-gradient) **Where can I get real-time updates from Gradient?** Follow our official channels and never miss a beat: * [Website](https://gradient.network/) * [X](https://x.com/Gradient_HQ) * [Discord](https://discord.com/invite/gradientnetwork) [PreviousCommunity Guidelines](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines) [NextOfficial Links](https://docs.gradient.network/learn-more/official-links) Last updated 2 months ago --- # Parallax | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Parallax is the operating system for sovereign AI. Under the hood, it is a distributed runtime and service fabric that turns heterogeneous machines into one traceable service you can build on. When a model is too big for one host, it is sharded into contiguous layer slices and distributed across your laptop, a lab GPU, and a teammate’s workstation, all orchestrated as one service. Each request takes the fastest path on a single host, across a LAN, or over the public internet, without a public IP or matching hardware. Parallax opens up a wide range of ways to host and run your own AI apps and agents that are completely your own, including coding copilots, personal assistants, vision and speech pipelines, and multi-agent simulations. At launch, Parallax supports **40+ open models** from **0.6B** to **trillion-class MoE** on **GPUs** and **Apple Silicon**, across **Windows, Linux, and macOS**. * Host your own AI cluster: [github.com/GradientHQ/parallax](http://github.com/GradientHQ/parallax) [PreviousThe Open Intelligence Stack](https://docs.gradient.network/the-open-intelligence-stack) [NextGradient Cloud](https://docs.gradient.network/enterprise-solutions/gradient-cloud) Last updated 19 days ago --- # Parallax | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Experience distributed inference with the [Gradient Chatbot](https://chat.gradient.network/) , powered by Parallax. Models available: `qwen3-235b-a22b` `gpt-oss-120b` Research Paper: [published](https://gradient.network/parallax.pdf) LLMs are reshaping how we think, build, and create, but their demand for tokens is outpacing what centralized infra can deliver. Chips saturated; Power grids strained; Intelligence remains locked behind high-cost silos. Parallax reimagines model inference as a global, collaborative process, one where models are no longer chained to centralized infrastructure, but are instead recomposed, executed, and verified across a global mesh of compute. The engine introduces 3 foundational shifts: 1. Intelligence sovereignty: serve models from the hardware you trust 2. Composable inference: GPUs, Apple Silicon, and desktops working in harmony 3. Latent compute: activate into the world’s untapped compute [](https://docs.gradient.network/the-open-intelligence-stack/parallax#the-architecture) The Architecture ------------------------------------------------------------------------------------------------------------- Parallax is a system specifically engineered for high-performance structured generation on decentralized machine networks. The system consists of three main layers: Runtime, Communication, and Worker. ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FDXA0ACle6QzMxC5buHeh%252Fblog_20250620_01%2520%281%29.png%3Falt%3Dmedia%26token%3D82f7a76b-3495-4359-9763-20fa95fb8e0a&width=768&dpr=4&quality=100&sign=1f7de350&sv=2) ### [](https://docs.gradient.network/the-open-intelligence-stack/parallax#runtime-layer) Runtime Layer The Parallax Runtime Layer is the core orchestration engine for high-throughput, server-side LLM serving on distributed, heterogeneous networks. It's composed of an Executor (control loop), Model Shard Holder, Request Manager, Scheduler, and Paged KV Cache Manager. As the first framework of its kind for the MLX ecosystem, the Parallax runtime pioneers professional-grade serving on Apple Silicon. ### [](https://docs.gradient.network/the-open-intelligence-stack/parallax#communication-layer) Communication Layer Manages gRPC and tensor streaming between peers, ensuring forward and backward passes succeed even if some nodes fail. Built on top of Hivemind’s Distributed Hash Table (DHT), a decentralized system that ensures fast, reliable information sharing without a central coordinator, to distribute values across peers. ### [](https://docs.gradient.network/the-open-intelligence-stack/parallax#worker-layer) Worker Layer Executes inference tasks across heterogeneous hardware platforms, ensuring optimal performance and scalability via a dual-platform approach: * GPU Workers: Use a modified version of SGLang (a fast serving framework for LLMs, which utilizes PyTorch with CUDA kernels to harness the full computational power of NVIDIA GPUs) with asynchronous batching for heterogeneous compute adaptations. * Apple Workers: We have engineered a state-of-the-art serving engine built upon our pioneering MLX-compatible runtime, with the integration of a highly optimized Metals kernel, including a Paged Flash Attention kernel, unlocking unprecedented inference efficiency and throughput on Apple Silicon. [](https://docs.gradient.network/the-open-intelligence-stack/parallax#the-swarm) The Swarm ----------------------------------------------------------------------------------------------- ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FYI6pOns3D2cjbT6jlylk%252Fblog_20250620_02%2520%281%29.png%3Falt%3Dmedia%26token%3D911a153f-bc42-4b21-b27b-cb1ac604541a&width=768&dpr=4&quality=100&sign=fcce99b1&sv=2) Parallax runs on a distributed architecture called the Swarm: a fully distributed machine mesh where your prompt is tokenized, segmented, and routed across nodes holding model shards. Each node executes its assigned layers of the LLM, passing hidden states forward until the full inference is complete. Optimal nodes are selected based on availability, compute, and latency. Coordination happens peer-to-peer via a DHT, enabling efficient routing, self-healing, and fault tolerance. [](https://docs.gradient.network/the-open-intelligence-stack/parallax#learn-more) Learn More ------------------------------------------------------------------------------------------------- Read the [blog](https://gradient.network/blog/parallax-world-inference-engine) for more details. Learn more about Parallax's architecture and benchmark results in the [research paper](https://gradient.network/parallax.pdf) .[](https://x.com/Gradient_HQ/status/1943581029953892628/photo/1) Last updated 2 months ago --- # Echo | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Research paper: [published](https://arxiv.org/pdf/2508.05387) Models: [open-sourced](https://huggingface.co/GradientResearch/models) As AI systems grow in scale and generality, RL has become a critical layer for alignment. However, most co-located RL frameworks face a deadlock: inference interrupts training, training delays inference. Echo is Gradient’s distributed RL framework, running on everyday consumer devices. [](https://docs.gradient.network/the-open-intelligence-stack/echo#dual-swarm-architecture) Dual Swarm Architecture ----------------------------------------------------------------------------------------------------------------------- Echo breaks the cycle by decoupling them into two independent swarms: * Inference on distributed devices (via [Parallax](https://docs.gradient.network/the-open-intelligence-stack/parallax) ) * Training on high-performance clusters ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FeUFaXhwNN6LcfAoYQcHD%252Fimage.png%3Falt%3Dmedia%26token%3D09ca5bbb-f784-4bd6-9586-61b0876171ed&width=768&dpr=4&quality=100&sign=68924ade&sv=2) [](https://docs.gradient.network/the-open-intelligence-stack/echo#echo-modes) Echo Modes --------------------------------------------------------------------------------------------- We have open-sourced several early explorations with Echo, including: * A 7B math model beating Qwen2.5–32B * A 30B Sokoban model outperforming DeepSeek-R1 & GPT-OSS-120B * A 32B LoRA logic model ≥99% accuracy See all models in our [Hugging Face Collection](https://huggingface.co/GradientResearch/models) . [](https://docs.gradient.network/the-open-intelligence-stack/echo#learn-more) Learn More --------------------------------------------------------------------------------------------- Read the [blog](https://gradient.network/blog/echo-distributed-reinforcement-learning) . Read the full [research paper](https://arxiv.org/pdf/2508.05387) . Last updated 2 months ago --- # Gradient Cloud | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) [Gradient Cloud](https://cloud.gradient.network/) is the all-in-one station for building with AI, powered by the Gradient distributed AI stack. Powered by Lattica, Parallax, and Echo, workloads are deployed and routed across a global network of hardware instead of centralized clusters. That’s how we unlock high throughput + low latency intelligence at low cost. Phase 1 is live with: • **Inference Endpoints** for leading open-source models • **Interactive Playground** with tunable params + one-click deploy All new accounts will be credited with a few million free tokens to jumpstart your AI ideas. You can find API details below: [API Reference Documentation](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) [PreviousParallax](https://docs.gradient.network/open-source/parallax) [NextAPI Reference Documentation](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) Last updated 2 months ago --- # Lattica | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Peer-to-peer video [streaming](https://explorer.gradient.network/) powered by Lattica. [](https://docs.gradient.network/the-open-intelligence-stack/lattica#from-sentry-nodes-to-lattica) From Sentry Nodes to Lattica ------------------------------------------------------------------------------------------------------------------------------------ During Sentry Node Open Beta, our community helped run one of the world’s largest decentralized connectivity experiments with over 2 billion peer-to-peer connections made across 190+ regions. That network has evolved into Lattica — a universal data communication protocol. Built on Gradient’s global peer-to-peer infrastructure, it tackles one of the core challenges in distributed AI: moving data across a heterogeneous, permissionless mesh without centralized intermediaries. [](https://docs.gradient.network/the-open-intelligence-stack/lattica#why-lattica-matters) Why Lattica Matters ------------------------------------------------------------------------------------------------------------------ As AI becomes more distributed and multi-agent, coordination is just as critical as compute. Lattica is built to move model weights, inference tokens, and file shards across a global machine mesh. At its core, Lattica powers everything needed to build the future of intelligence—open, agentic, and alive at the edge. As the universal data motion engine, it ensures data flows fast, securely, and reliably—powering multiple layers of our distributed AI stack: from routing model parameters to coordinating distributed inference and enabling agent communication. [](https://docs.gradient.network/the-open-intelligence-stack/lattica#see-lattica-in-motion) See Lattica in Motion ---------------------------------------------------------------------------------------------------------------------- Lattica usually runs invisibly, so we put it in motion within the [Gradient Explorer](https://explorer.gradient.network/) . ![](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FzWVkZHonFFSlcrRr0pRC%252FGtzT_rtbQAArwBn%2520%281%29.jpeg%3Falt%3Dmedia%26token%3D647a9f70-2777-4867-b3af-d73e77117914&width=768&dpr=4&quality=100&sign=14a2fb54&sv=2) We built a decentralized video streaming experience in one of the most constrained and unpredictable environments: your browser. Read the [blog](https://gradient.network/blog/lattica-universal-data-motion-engine) to learn more. Last updated 2 months ago --- # User Experiences | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) There are many ways to experience Gradient technology with the following products, tailor-made for general users. ![Cover](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FHOpaWebTeSR703sw0kpu%252F120b.png%3Falt%3Dmedia%26token%3D9b606ee8-a725-42aa-ae60-c945f35d3620&width=490&dpr=4&quality=100&sign=e0f86a69&sv=2) [**Gradient Chatbot**](https://chat.gradient.network/) Distributed inference with top LLMs, powered by Parallax. ![Cover](https://docs.gradient.network/~gitbook/image?url=https%3A%2F%2F778817341-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FGc5DgPM12k3y1ReDHVhq%252Fuploads%252FzWVkZHonFFSlcrRr0pRC%252FGtzT_rtbQAArwBn%2520%281%29.jpeg%3Falt%3Dmedia%26token%3D647a9f70-2777-4867-b3af-d73e77117914&width=490&dpr=4&quality=100&sign=14a2fb54&sv=2) [**Gradient Explorer**](https://explorer.gradient.network/) Glance through network stats and experience Lattica with distributed video streaming [PreviousAPI Reference Documentation](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) [NextSentry Node Open Beta (Concluded)](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded) Last updated 2 months ago --- # Edge Host Pilot Program | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) Status: invite-only. The team will contact eligible applicants regarding onboarding. To scale distributed compute for AI, we recently launched the Edge Host Pilot Program, inviting enterprises and individuals with powerful, high-availability compute resources to collaborate in shaping the future of distributed intelligence. If you are: * A data center with idle or underutilized bandwidth or GPU resources, or * An individual contributor with powerful, high-availability compute resources, We have already started contacting qualified participants for the next steps. Apply to be an Edge Host on Gradient Network [here](https://t.co/1Yr1BBNiFY) . Last updated 2 months ago --- # FAQ | Gradient [Open Sourcing Parallax: Your Sovereign AI OS\ \ Learn More](https://gradient.network/blog/parallax-the-sovereign-ai-os) [](https://docs.gradient.network/learn-more#general) General ----------------------------------------------------------------- #### [](https://docs.gradient.network/learn-more#what-is-gradient-building) **What is Gradient building?** > Gradient is building the world’s first fully distributed AI stack — a peer-powered infrastructure where intelligence is hosted, served, and owned by the people. #### [](https://docs.gradient.network/learn-more#what-makes-gradient-different) **What makes Gradient different?** > Instead of running models in closed datacenters, Gradient is distributing AI workloads across a global mesh of consumer devices and compatible datacenters. This reduces cost, improves resilience, and democratizes access. * * * ### [](https://docs.gradient.network/learn-more#research) Research #### [](https://docs.gradient.network/learn-more#what-has-gradient-done-in-the-field-of-distributed-ai) What has Gradient done in the field of distributed AI? > We have released research and products on: [Lattica](https://docs.gradient.network/the-open-intelligence-stack/lattica) > (peer-to-peer data communication) [Parallax](https://docs.gradient.network/the-open-intelligence-stack/parallax) > (distributed inference) [Echo](https://docs.gradient.network/the-open-intelligence-stack/echo) > (distributed reinformcement learning) More work on multi-agent collaboration, self-evolving agentic systems are more are in the pipeline. * * * ### [](https://docs.gradient.network/learn-more#gradient-cloud) Gradient Cloud **What is Gradient Cloud?** > [Gradient Cloud](https://docs.gradient.network/enterprise-solutions/gradient-cloud) > is the dev-facing, one-stop solution to access Gradient's distributed AI stack. In phase 1, it's offering inference endpoints, APIs, and a Playground to build and deploy AI workloads. More features coming in phase 2. **Is Gradient Cloud compatible with OpenAI-style APIs?** > Yes. Core endpoints follow the same schema, with Gradient-native extensions for scheduling and privacy controls. **What models are available?** > Leading open-source LLMs, with more added continuously. Model IDs are published in the [API Reference](https://docs.gradient.network/enterprise-solutions/gradient-cloud/api-reference-documentation) > . #### [](https://docs.gradient.network/learn-more#sentry-nodes) Sentry Nodes **Is the Sentry Node Open Beta still active?** > No. The Open Beta has concluded and Sentry Nodes are no longer accumulating new Uptime or Taps rewards. The sections on Sentry Nodes within this documentation is for reference purposes only. * * * ### [](https://docs.gradient.network/learn-more#whats-next) **What’s next** > The team is constantly cooking. Stay tuned for more seamless, tangible experience, where every community member will gain direct access to the full power of distributed intelligence. **Scam Alert** We've received multiple reports of phishing emails impersonating Gradient. These emails may ask for donations or prompt you to interact with third-party URLs. These are **100% scams**. A closer look at the sender's address will easily reveal their true identity. - Do NOT interact with any unknown site. Check the URL letter by letter. - Do NOT respond to emails claiming to represent Gradient. - Gradient will NEVER ask for donations or request payments via email or DMs. - Trust only information from our official channels. ### [](https://docs.gradient.network/learn-more#where-can-i-get-real-time-updates-from-gradient) **Where can I get real-time updates from Gradient?** Follow our official channels and never miss a beat: * [Website](https://gradient.network/) * [X](https://x.com/Gradient_HQ) * [Discord](https://discord.com/invite/gradientnetwork) [PreviousCommunity Guidelines](https://docs.gradient.network/user-products/sentry-node-open-beta-concluded/sentry-nodes-user-guide-legacy/rewards-concluded/community-guidelines) [NextOfficial Links](https://docs.gradient.network/learn-more/official-links) Last updated 2 months ago ---