Documentation Home
Welcome to Cxmpute documentation - your guide to distributed AI services
Welcome to the Cxmpute documentation! Cxmpute is a distributed AI/Compute services platform that connects users who need AI services with providers who offer compute resources, creating a global network of AI compute power.
Quick Start
For Users
- Get Started: Create an account and start using AI services in minutes
- API Reference: Complete API documentation for all endpoints
- Service Guides: Learn about specific services like chat, embeddings, TTS, and scraping
For Providers
- Become a Provider: Download the CLI and start earning rewards
- Provider Guide: Complete setup instructions and earning tips
- Rewards System: Learn about earnings and referrals
What is Cxmpute?
Cxmpute provides inference and related services powered by a global network of nodes run by providers. We offer:
- LLM Inference: OpenAI-compatible chat completions with dozens of models
- Text Embeddings: High-quality vector embeddings for your applications
- Text-to-Speech: Natural voice synthesis with multiple voice models
- Web Scraping: Reliable content extraction and markdown conversion
- Tool Use & JSON: Structured outputs and function calling capabilities
Service Documentation
AI Services
- Text-to-Text (LLM) - Chat completions and text generation
- Embeddings - Vector embeddings for semantic search
- Text-to-Speech - Audio generation from text
- Web Scraping - Content extraction and processing
- Tool Use & JSON - Structured outputs and function calling
- Advanced LLMs - Advanced features for large language models
Platform
- User Guide - Complete API reference and getting started
- Provider Guide - How to become a compute provider
- Rewards System - Earning rewards and referral program
- About Cxmpute - Platform overview and architecture
Key Features
🚀 Easy to Use
- OpenAI-compatible APIs - just change the base URL
- Simple authentication with API keys
- Comprehensive documentation and examples
🌍 Global Network
- Distributed provider network for low latency
- Automatic load balancing and health monitoring
- Geographic distribution for optimal performance
💰 Cost-Effective
- Currently free during testnet phase
- Future pricing to be announced (TBA)
- Competitive rates through decentralized provider network
🔒 Secure & Reliable
- Enterprise-grade security and privacy
- 99.5%+ uptime with automatic failover
- Provider verification and health monitoring
Getting Started
1. Create an Account
Visit the Cxmpute Dashboard to create your account and get your API key.
2. Make Your First Request
curl -X POST https://cxmpute.cloud/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "X-User-Id: YOUR_USER_ID" \
-H "Content-Type: application/json" \
-d '{
"model": "llama3.1:8b",
"messages": [{"role": "user", "content": "Hello, world!"}]
}'3. Explore Services
Try different AI services:
- Chat completions for conversations and text generation
- Embeddings for semantic search and RAG
- Text-to-speech for voice applications
- Web scraping for data collection
Testnet Phase
🎉 All services are currently free! During our testnet phase, you can use all Cxmpute services without charges. Pricing for the mainnet launch is to be determined (TBD).
Join our Discord community to stay updated on pricing announcements, give feedback, and connect with other developers building with Cxmpute.
Community & Support
- Discord: Join our community for support and latest news
- GitHub: Check out our open source code
- Email: Contact us at support@cxmpute.cloud
Model Catalog
Explore our full range of available models at cxmpute.cloud/models.
Ready to get started? Create your account or become a provider today!