Axon
Overview
Axon is a unified AI chat platform that aggregates 50+ models from 15 providers into a single interface. Instead of juggling separate subscriptions for ChatGPT, Claude, Gemini, and others, users get access to all of them in one place — with the ability to switch models mid-conversation.
The platform runs on a freemium SaaS model with 19 free models available out of the box, and a Pro plan for premium models with higher usage limits.
What Users Can Do
- Chat with 50+ AI models — GPT, Claude, Gemini, Llama, DeepSeek, Mistral, and more from a single interface
- Switch models mid-conversation — Compare responses from different models without losing context
- Generate images — Create AI-generated images with automatic cloud storage and CDN delivery
- Upload files — Drag & drop files for multimodal conversations
- Track usage — View token counts, response times, and monthly usage at a glance
- Stream responses in real-time — See AI responses as they're generated, with support for reasoning/thinking modes
- Render rich content — Markdown, syntax-highlighted code, and LaTeX math equations
- Pick up where you left off — Persistent conversation history with auto-generated titles across devices
Why I Built This
I was frustrated with managing multiple AI subscriptions and constantly switching between different chat interfaces. Each provider has its own UI, billing, and limitations. I wanted a single platform where I could access all the models I use daily, compare their outputs side-by-side, and manage everything through one subscription.
Building Axon also gave me the opportunity to work with a full SaaS stack end-to-end — from OAuth and Stripe billing to real-time streaming and cloud storage.
Tech Stack
- Next.js 16, React 19, TypeScript
- Hono on Bun (backend API)
- PostgreSQL (Neon) + Drizzle ORM
- Vercel AI SDK + OpenRouter
- Better Auth (Google & GitHub OAuth)
- Stripe (payments & subscriptions)
- Cloudflare R2 (image storage)
- Tailwind CSS 4, shadcn/ui
- Turborepo (monorepo)