Home

Gatewayz Backend Wiki

Universal AI Gateway - Complete Documentation Hub

Production-ready AI gateway providing unified access to 100+ AI models across 17+ providers with enterprise security, credit management, and comprehensive monitoring.

---

Quick Navigation

Section	Description
Getting Started	New to the project? Start here
Features	Feature documentation and guides
Deployment	Deploy to production platforms
Monitoring	Track errors and performance
Security	Security and compliance
Integrations	AI provider integrations
Development	Developer workflows
API Reference	Complete API documentation

---

Getting Started

New developers start here:

Document	Description
Quick Start	Get running in 15 minutes
Complete Setup Guide	Full development environment setup
Environment Setup	Configure environment variables
Architecture	System architecture overview
Project Structure	Codebase organization

First-Time Setup

# 1. Clone and navigate
git clone <repo-url>
cd gatewayz-backend

# 2. Install dependencies
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

# 3. Configure environment
cp .env.example .env
# Edit .env with your keys

# 4. Run server
python src/main.py

# 5. Test
curl http://localhost:8000/health

---

Core Features

API & Inference

Feature	Documentation
Chat Completions	OpenAI-compatible /v1/chat/completions endpoint
Messages API	Anthropic-compatible Claude API
Image Generation	AI-powered image creation
Model Catalog	Browse 100+ models across providers
Model Health	Real-time model availability tracking
Model Sync	Automated catalog synchronization

User Management

Feature	Documentation
Authentication	Privy integration + custom auth
API Keys	Encrypted key management with scopes
User Profiles	Account management and settings
Activity Logging	Comprehensive activity tracking
Audit Logs	Security event logging
Roles & Permissions	RBAC implementation

Billing & Credits

Feature	Documentation
Pricing System	Token-based pricing across models
Credit Management	Real-time credit tracking and deduction
Stripe Integration	Payment processing and subscriptions
Subscription Plans	Tiered subscription management
Free Trials	3-day trial with $10 credits
Coupons	Discount codes and promotions
Referral System	User referral rewards

Performance & Reliability

Feature	Documentation
Rate Limiting	Redis-backed rate limiting
Caching	Response and model catalog caching
Failover	Automatic provider failover
Connection Pooling	Optimized database connections
Request Prioritization	Priority queue for critical requests

Advanced Features

Feature	Documentation
Chat History	Persistent conversation management
Analytics	Usage analytics with PostHog
Feature Flags	A/B testing with Statsig
Notifications	Email notifications via Resend
Webhooks	Stripe webhook handling

---

Deployment

Platform-Specific Guides

Platform	Quick Start	Detailed Guide
Railway	Railway Quick Start	Railway Setup
Vercel	Vercel Quick Start	Vercel Deployment
Docker	Docker Quick Start	Docker Guide

Deployment Topics

Topic	Documentation
Auto-Deployment	Setup automated deployments
Staging Environment	Configure staging
Database Migrations	Supabase Migrations CI
GitHub Secrets	Configure CI/CD secrets
Environment Config	Environment differentiation

---

Monitoring & Observability

Error Tracking

Tool	Documentation
Sentry	Error monitoring setup
PostHog	Alternative error tracking
Audit Logs	Security event logging

Performance

Topic	Documentation
Metrics	Prometheus metrics
Performance Monitoring	Track and optimize performance
Health Checks	System health monitoring
OpenTelemetry	Distributed tracing

Dashboards

Dashboard	Documentation
Grafana	Setup Grafana dashboards
Monitoring System	Complete Monitoring

---

Security

Topic	Documentation
API Key Security	Encryption, rotation, scopes
Secrets Management	Managing sensitive data
Staging Security	Secure staging environment
Incident Response	Handle security incidents
Database Security	Secure database access

---

Provider Integrations

Supported Providers (17+)

Provider	Type	Documentation
OpenRouter	Multi-model gateway	Primary provider
Google Vertex AI	Enterprise AI	Vertex Setup
Alibaba Cloud	Chinese market	Alibaba Integration
Cerebras	Fast inference	Native integration
DeepInfra	Open models	Native integration
Fireworks AI	Optimized inference	Native integration
Groq	Ultra-fast LLMs	Native integration
HuggingFace	Model hub	HF Integration
Together AI	Open source models	Native integration
Featherless	Cost-effective	Native integration
Chutes	Specialized provider	Native integration
+6 more	Various	See Integration Guide

Integration Guides

Topic	Documentation
Add New Provider	Integration guide
OneRouter	OneRouter setup
Novita SDK	Novita integration
Frontend Integration	Connect frontend

---

Development

Workflows

Topic	Documentation
Pre-Push Checklist	Check before pushing
Testing Locally	Test GitHub Actions
Live API Testing	Test against live APIs
Failover Testing	Test failover scenarios
Migration Sync	Database migrations

Testing

Topic	Documentation
Test Suite	Running tests
Database Testing	Test database
API Testing	Apidog runner setup
OpenRouter Testing	Automated validation

---

API Reference

Resource	Documentation
Complete API Docs	API Reference
OpenAPI Spec	Access at /docs endpoint
Chat API	Chat completions
Images API	Image generation
Admin API	Admin operations

---

Advanced Topics

Architecture

Topic	Documentation
System Architecture	Architecture
Database Schema	Database design
Service Layer	Business logic organization
Provider Abstraction	Multi-provider pattern

Automation

Topic	Documentation
Auto-Merge PRs	Auto-merge setup
Automated Testing	CI/CD testing
Model Sync	Automated catalog sync

---

Troubleshooting

Topic	Documentation
Common Issues	Troubleshooting
Error Fixes	Recent fixes
Auth Timeouts	Fix auth issues
Prometheus Fixes	Monitoring fixes

---

Quick Reference

Key Statistics

• Total Features: 25+ major features
• Supported Providers: 17+ AI providers
• API Endpoints: 50+ endpoints
• Available Models: 100+ models
• Test Coverage: 85%+
• Response Time: <100ms avg

Technology Stack

• Framework: FastAPI 0.104.1
• Database: Supabase (PostgreSQL)
• Cache: Redis 5.0.1
• Payments: Stripe 13.0.1
• Email: Resend 0.8.0
• Analytics: PostHog, Statsig
• Monitoring: Sentry, Prometheus

External Links

• Supabase Dashboard
• Railway Dashboard
• Stripe Dashboard
• Sentry Dashboard

---

Documentation Standards

When contributing documentation:

• Use clear, concise language
• Include code examples
• Add diagrams for complex flows
• Keep token usage efficient
• Cross-reference related pages
• Update this index when adding pages

---

Search Tips

I want to...	Go to...
Set up my dev environment	Complete Setup Guide
Deploy to production	Railway Quick Start
Track errors	Error Monitoring
Add a new provider	Integration Guide
Understand pricing	Pricing System
Secure my API	Security
Run tests locally	Testing Workflows
Fix a bug	Troubleshooting

---

Last Updated: December 2024 Maintained By: Gatewayz Development Team Questions? Check Troubleshooting or open an issue