Chuzom — Extend Your Claude Quota. 3× Longer Sessions.
⭐ Star on GitHub if Chuzom saves your quota ⭐
Help other developers discover automatic LLM routing
The Problem
You're on Claude Pro ($20/mo), Max ($100/mo), or Max ($200/mo) — a flat subscription, not pay-per-token.
But Claude Code routes every request through your quota: file reads, quick questions, routine edits, and complex reasoning all burn the same limited budget. Claude throttles after roughly 40–50 messages in a 5-hour rolling window.
The result: your session hits the wall in under 2 hours, and you wait.
| Prompt | Quota burned | Actually needs Claude? |
|---|
| "What does this function return?" | ✗ Yes | No |
| "List files matching *.test.ts" | ✗ Yes | No |
| "Write a test for this function" | ✗ Yes | Probably not |
| "Re-architect this auth system" | ✓ Yes | Yes |
Simple questions and complex reasoning cost the same quota. That's the inefficiency Chuzom fixes.
The Solution
Chuzom routes each prompt to the cheapest capable model before spending Claude quota.
Your IDE (Claude Code, Cursor, etc)
↓
[Chuzom Smart Router] ← analyzes complexity & task type
↓
├─ Simple tasks? → Ollama (local, free) 🌳
├─ Moderate tasks? → Codex CLI / Gemini CLI (free via your subscriptions)
└─ Complex tasks? → Claude (only when it truly needs it) 🔥
↓
Result + streaming progress + quota savings banner
🎯 chuzom → gemini-2.5-flash · code/moderate · 342ms · saved Claude quota!
A typical developer session burns ~200,000 Claude tokens. Routing ~80% of prompts to free models saves ~160,000 Claude tokens per session — the difference between hitting the limit in 2 hours vs. working a full uninterrupted day.
| Tool | Cost | Best for |
|---|
| Ollama (local) | Free | Simple questions, syntax lookups, file ops |
| Codex CLI | Free (via GitHub Copilot) | Code generation, refactors, test writing |
| Gemini CLI | Free (via Google account) | Moderate reasoning, explanations, summaries |
| Claude | Your subscription quota | Complex reasoning, long context, architecture |
Why People Install This
AI coding tools send too many prompts to premium models by default.
That means:
- ❌ You waste paid tokens on simple questions
- ❌ You burn through Claude, Gemini, or OpenAI quota faster than necessary
- ❌ You stop working when one provider is rate-limited or down
Chuzom sits between your coding tool and your model providers. It classifies each prompt, tries the cheapest capable model first, and falls back automatically when needed.
You keep the same workflow. The router changes the model choice underneath.
⏱️ 3–5× Longer Sessions
Route 80% of prompts to free models — hit quota limits far less often
|
✅ Quality Preserved
Premium models only when the task truly needs it
|
🛡️ Quota Protected
Auto-downgrade near limits. No more rate-limit walls
|
⚙️ Zero Config
Works out of the box with Claude Pro/Max subscription
|
Real-World Savings
Typical Claude Code heavy user — mix of questions, code review, and debugging (~1,000 prompts/week):
| Approach | Claude tokens/week | Sessions per day before limit | Extra spend (if buying API) |
|---|
| All prompts → Claude | ~200,000 | 1–2 sessions | $18–40/week |
| Chuzom (smart routing) | ~40,000 | 6–8 sessions | $2–6/week |
