Model Routing Middleware
/install model-routing-middleware
Model Routing — Intelligent Model Selection Middleware
Automatically select the best LLM model and think mode based on task type, context size, and response confidence. Cut API costs 40-70% by routing simple tasks to fast models and complex tasks to capable ones.
How It Works
User message → Task Classifier → Model Router → Best Model → Response
↓
Low confidence? → Escalate to stronger model
Quick Start
# config.yaml
models:
casual_chat:
model: qwen3-14b
think: false
coding:
model: qwen-coder
think: true
reasoning:
model: deepseek-r1
think: true
long_context:
model: glm-5.1
think: false
from router import get_router
router = get_router()
result = await router.route("Write a Python web scraper")
# → Routes to qwen-coder with think=True
Features
- Task-type classification (coding, reasoning, chat, summarization)
- Per-model think mode configuration
- Confidence-based escalation (retry with stronger model)
- Context management and compaction at 55% threshold
- Hot-reload configuration (no restart needed)
- 83 tests passing
Cost Savings
| Task Type | Without Routing | With Routing | Savings |
|---|---|---|---|
| Casual chat | GPT-4 ($0.03/1K) | Qwen3-14B (local) | ~100% |
| Coding | GPT-4 ($0.03/1K) | Qwen-Coder (local) | ~95% |
| Hard reasoning | GPT-4 ($0.03/1K) | DeepSeek-R1 (local) | ~90% |
License
MIT
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install model-routing-middleware - After installation, invoke the skill by name or use
/model-routing-middleware - Provide required inputs per the skill's parameter spec and get structured output
What is Model Routing Middleware?
Intelligent model selection middleware for AI agents. Route tasks to the best model, manage context, and cut API costs 40-70%. It is an AI Agent Skill for Claude Code / OpenClaw, with 50 downloads so far.
How do I install Model Routing Middleware?
Run "/install model-routing-middleware" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Model Routing Middleware free?
Yes, Model Routing Middleware is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Model Routing Middleware support?
Model Routing Middleware is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Model Routing Middleware?
It is built and maintained by larios613-hub (@larios613-hub); the current version is v1.0.0.