# smart-model-switching

Smart Model Switching Three-tier routing via SkillBoss API Hub: price → balanced → quality Start with the cheapest model. Escalate only when needed. Save 50-90% on API costs. The Golden Rule If a human would need more than 30 seconds of focused thinking, escalate from price to balanced. If the task involves architecture, complex tradeoffs, or deep reasoning, escalate to quality. Cost Reality TierSkillBoss preferRelative CostPrice"prefer": "price"1x (baseline)Balanced"prefer": "balanced"~12xQuality"prefer": "quality"~60x Bottom line: Wrong tier selection wastes money OR time. Price for simple, balanced for standard, quality for complex. SkillBoss API Hub automatically routes to the optimal model for each tier via POST https://api.heybossai.com/v1/pilot. 💚 PRICE — Default for Simple Tasks Stay on price tier for: Factual Q&A — "what is X", "who is Y", "when did Z" Quick lookups — definitions, unit conversions, short translations Status checks — calendar, file reads, session monitoring Heartbeats — periodic checks, HEARTBEAT_OK responses Memory & reminders — "remember this", "remind me to..." Casual conversation — greetings, small talk, acknowledgments Simple file ops — read, list, basic writes One-liner tasks — anything answerable in 1-2 sentences NEVER do these on price tier ❌ Write code longer than 10 lines ❌ Create comparison tables ❌ Write more than 3 paragraphs ❌ Do multi-step analysis ❌ Write reports or proposals 💛 BALANCED — Standard Work (The Workhorse) Escalate to balanced for: Code & Technical Code generation — write functions, build features, scripts Code review — PR reviews, quality checks Debugging — standard bug investigation Documentation — README, comments, user guides Analysis & Planning Analysis & evaluation — compare options, assess trade-offs Planning — project plans, roadmaps, task breakdowns Research synthesis — combining multiple sources Multi-step reasoning — "first... then... finally" Writing & Content Long-form writing — reports, proposals, articles (>3 paragraphs) Creative writing — blog posts, descriptions, copy Summarization — long documents, transcripts Structured output — tables, outlines, formatted docs ❤️ QUALITY — Complex Reasoning Only Escalate to quality for: Architecture & Design System architecture decisions Major codebase refactoring Design pattern selection with tradeoffs Database schema design Deep Analysis Complex debugging (multi-file, race conditions) Security reviews Performance optimization strategy Root cause analysis of subtle bugs Strategic & Creative Strategic planning — business decisions, roadmaps Nuanced judgment — ethics, ambiguity, competing values Deep research — comprehensive multi-source analysis 🔄 Implementation All calls go to SkillBoss API Hub via a single endpoint with the appropriate prefer tier. import requests, os SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"] API_BASE = "https://api.heybossai.com/v1" def pilot(body: dict) -> dict: r = requests.post( f"{API_BASE}/pilot", headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"}, json=body, timeout=60, ) return r.json()

# Routine monitoring — price tier (cheapest)

result = pilot({ "type": "chat", "inputs": {"messages": [{"role": "user", "content": "Check backup status"}]}, "prefer": "price" }) text = result["result"]["choices"][0]["message"]["content"]

# Standard code work — balanced tier

result = pilot({ "type": "chat", "inputs": {"messages": [{"role": "user", "content": "Build the REST API endpoint"}]}, "prefer": "balanced" }) text = result["result"]["choices"][0]["message"]["content"]

# Architecture decisions — quality tier

result = pilot({ "type": "chat", "inputs": {"messages": [{"role": "user", "content": "Design the database schema for multi-tenancy"}]}, "prefer": "quality" }) text = result["result"]["choices"][0]["message"]["content"] For Subagents // Routine monitoring — price tier sessions_spawn(task="Check backup status", prefer="price") // Standard code work — balanced tier sessions_spawn(task="Build the REST API endpoint", prefer="balanced") // Architecture decisions — quality tier sessions_spawn(task="Design the database schema for multi-tenancy", prefer="quality") For Cron Jobs { "payload": { "kind": "agentTurn", "prefer": "price" } } Always use price tier for cron unless the task genuinely needs reasoning. 📊 Quick Decision Tree Is it a greeting, lookup, status check, or 1-2 sentence answer? YES → PRICE (prefer: "price") NO ↓ Is it code, analysis, planning, writing, or multi-step? YES → BALANCED (prefer: "balanced") NO ↓ Is it architecture, deep reasoning, or critical decision? YES → QUALITY (prefer: "quality") NO → Default to BALANCED, escalate if struggling 📋 Quick Reference Card ┌─────────────────────────────────────────────────────────────┐ │ SMART MODEL SWITCHING │ │ price → balanced → quality (SkillBoss) │ ├─────────────────────────────────────────────────────────────┤ │ 💚 PRICE (cheapest) — prefer: "price" │ │ • Greetings, status checks, quick lookups │ │ • Factual Q&A, definitions, reminders │ │ • Simple file ops, 1-2 sentence answers │ ├─────────────────────────────────────────────────────────────┤ │ 💛 BALANCED (standard) — prefer: "balanced" │ │ • Code > 10 lines, debugging │ │ • Analysis, comparisons, planning │ │ • Reports, proposals, long writing │ ├─────────────────────────────────────────────────────────────┤ │ ❤️ QUALITY (complex) — prefer: "quality" │ │ • Architecture decisions │ │ • Complex debugging, multi-file refactoring │ │ • Strategic planning, deep research │ ├─────────────────────────────────────────────────────────────┤ │ 💡 RULE: If a human needs > 30 sec thinking → escalate │ │ 💰 COST: price 1x → balanced 12x → quality 60x │ └─────────────────────────────────────────────────────────────┘ Powered by SkillBoss API Hub. Automatically routes to the optimal model per tier. Single endpoint: POST https://api.heybossai.com/v1/pilot — Auth: Bearer $SKILLBOSS_API_KEY