clawrouter
Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.
About this skill
ClawRouter is an essential `openclaw` skill designed to optimize LLM inference costs by intelligently routing each request to the most cost-effective yet capable model. It supports a diverse ecosystem of 41 models from leading providers including OpenAI, Anthropic, Google, DeepSeek, and xAI, all accessible through a unified interface. Users can expect savings of up to 67% on their LLM expenses, making high-volume AI interactions more economical. The skill operates by classifying each incoming request into one of four complexity tiers: SIMPLE, MEDIUM, COMPLEX, or REASONING. Based on this classification, it then directs the request to the cheapest model best suited for that specific task. For example, simple queries might go to Gemini Flash for maximum savings, while complex code generation could be routed to Claude Opus for optimal quality. Most routing decisions are made swiftly by rules (<1ms), with only ambiguous queries requiring a minimal-cost LLM classifier. Beyond automated cost optimization, ClawRouter offers flexibility, allowing users to enable smart routing globally or to pin a specific model when precise control is needed. This combination of intelligent automation and user-defined control ensures that both cost efficiency and task-specific performance requirements are met, streamlining LLM usage for a wide range of applications.
Best use case
ClawRouter is ideal for developers, businesses, and individual users who frequently interact with various LLMs and are looking to drastically cut down on their inference expenses. It's particularly beneficial for those managing high volumes of diverse AI tasks where model selection can significantly impact operational costs, allowing them to optimize expenditure without compromising on quality or performance.
Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.
Users should expect a substantial reduction in their overall LLM inference expenditures, coupled with intelligent model selection tailored to the complexity of each request.
Practical example
Example input
openclaw chat "Write a 50-word summary of the American Civil War's causes and main outcome."
Example output
[ClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92)
Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%When to use this skill
- To significantly reduce your overall LLM inference costs.
- When needing to access a wide array of LLM models from different providers through a single interface.
- For automatically selecting the most appropriate and cost-effective model for a given task's complexity.
- If you want to simplify LLM provider management and billing into one 'wallet' via openclaw.
When not to use this skill
- If you exclusively use a single, specific LLM and have no interest in cost optimization or alternative models.
- If your LLM usage is extremely low, making the potential cost savings negligible.
- If you require absolute, manual control over every single model invocation without any automated routing.
- If you prefer to manage direct API keys and accounts for each individual LLM provider.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/clawrouter/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How clawrouter Compares
| Feature / Agent | clawrouter | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# ClawRouter
Smart LLM router that saves 67% on inference costs by routing each request to the cheapest model that can handle it. 41 models across 5 providers, all through one wallet.
## Install
```bash
openclaw plugins install @blockrun/clawrouter
```
## Setup
```bash
# Enable smart routing (auto-picks cheapest model per request)
openclaw models set blockrun/auto
# Or pin a specific model
openclaw models set openai/gpt-4o
```
## How Routing Works
ClawRouter classifies each request into one of four tiers:
- **SIMPLE** (40% of traffic) — factual lookups, greetings, translations → Gemini Flash ($0.60/M, 99% savings)
- **MEDIUM** (30%) — summaries, explanations, data extraction → DeepSeek Chat ($0.42/M, 99% savings)
- **COMPLEX** (20%) — code generation, multi-step analysis → Claude Opus ($75/M, best quality)
- **REASONING** (10%) — proofs, formal logic, multi-step math → o3 ($8/M, 89% savings)
Rules handle ~80% of requests in <1ms. Only ambiguous queries hit the LLM classifier (~$0.00003 per classification).
## Available Models
41 models including: gpt-5.2, gpt-4o, gpt-4o-mini, o3, o1, claude-opus-4.6, claude-sonnet-4.6, claude-haiku-4.5, gemini-3.1-pro, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, deepseek-chat, deepseek-reasoner, grok-3, grok-3-mini.
## Example Output
```
[ClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92)
Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%
```Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成（播客、视频、幻灯片、测验、思维导图等）、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述