{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-smart-router",
    "name": "Openclaw Smart Router",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/AtlasPA/openclaw-smart-router",
    "canonicalUrl": "https://clawhub.ai/AtlasPA/openclaw-smart-router",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-smart-router",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-smart-router",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "API-REFERENCE.md",
      "DATABASE-IMPLEMENTATION.md",
      "hooks/provider-after.js",
      "hooks/request-before.js",
      "hooks/session-end.js",
      "IMPLEMENTATION.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/openclaw-smart-router"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/openclaw-smart-router",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-smart-router/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-smart-router/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-smart-router/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "OpenClaw Smart Router",
        "body": "Save 30-50% on model costs through intelligent, automatic model selection."
      },
      {
        "title": "What is it?",
        "body": "The first OpenClaw skill that automatically routes requests to optimal models based on complexity analysis and budget constraints. Stops you from wasting money on expensive models for simple tasks. Learns from your usage patterns and gets smarter over time."
      },
      {
        "title": "Key Features",
        "body": "🎯 30-50% Cost Savings - Automatic model selection based on task complexity\n🧠 Complexity Analysis - Scores tasks 0.0-1.0 and selects appropriate model\n💰 Budget Awareness - Respects spending limits and cost targets\n📊 Pattern Learning - Learns which models work best for your tasks\n🔄 Multi-Provider - Works with Anthropic, OpenAI, Google, and more\n💸 x402 Payments - Agents can pay for unlimited routing (0.5 USDT/month)"
      },
      {
        "title": "Free vs Pro Tier",
        "body": "Free Tier:\n\n100 routing decisions per day\nAutomatic complexity analysis\nBasic model selection\nCost tracking\n\nPro Tier (0.5 USDT/month):\n\nUnlimited routing decisions\nAdvanced pattern learning\nCustom routing rules\nDetailed analytics and ROI tracking\nBudget optimization"
      },
      {
        "title": "Installation",
        "body": "claw skill install openclaw-smart-router"
      },
      {
        "title": "Commands",
        "body": "# View routing stats\nclaw router stats\n\n# Analyze complexity\nclaw router analyze \"Your task description...\"\n\n# View routing history\nclaw router history --limit=10\n\n# Show cost savings\nclaw router savings\n\n# Open dashboard\nclaw router dashboard\n\n# Subscribe to Pro\nclaw router subscribe"
      },
      {
        "title": "How It Works",
        "body": "Intercepts requests - Hooks before each API call\nAnalyzes complexity - Scores task from 0.0 (simple) to 1.0 (expert)\nChecks budget - Considers spending limits\nSelects model - Chooses optimal model:\n\nSimple (0.0-0.3) → Haiku/GPT-3.5\nMedium (0.3-0.6) → Sonnet/GPT-4-Turbo\nComplex (0.6-0.8) → Opus/GPT-4\nExpert (0.8-1.0) → Opus/GPT-4\n\n\nRoutes request - Sends to selected model\nLearns from result - Tracks success and adapts"
      },
      {
        "title": "Complexity Scoring",
        "body": "What makes a task complex?\n\nContext length (more context = higher complexity)\nCode presence (code analysis scores higher)\nError messages (debugging is complex)\nTask type (writing < coding < reasoning < research)\nQuestion complexity (multiple parts, nested logic)\nSpecificity (vague requests need stronger models)\n\nExamples:\n\nSimple (0.0-0.3) → Haiku:\n\n\"What's the current time?\"\n\"Format this JSON\"\n\"Fix typo in variable name\"\n\nMedium (0.3-0.6) → Sonnet:\n\n\"Refactor this class to use interfaces\"\n\"Write unit tests for this function\"\n\"Explain how React hooks work\"\n\nComplex (0.6-0.8) → Opus:\n\n\"Debug this multi-threaded race condition\"\n\"Design a scalable caching strategy\"\n\"Optimize this algorithm for performance\"\n\nExpert (0.8-1.0) → Opus:\n\n\"Design a distributed system architecture\"\n\"Solve this novel algorithmic problem\"\n\"Research and synthesize from multiple sources\""
      },
      {
        "title": "Use Cases",
        "body": "Reduce model costs by 30-50% automatically\nStop manually switching between models\nBudget-aware routing for cost control\nLearn optimal model selection from patterns\nTrack spending and ROI over time"
      },
      {
        "title": "Example 1: Development Work",
        "body": "Without Smart Router:\n- 100 requests/day to Opus\n- $0.015 per request\n- Monthly: $45\n\nWith Smart Router:\n- 30 requests to Haiku ($0.90)\n- 50 requests to Sonnet ($7.50)\n- 20 requests to Opus ($9.00)\n- Monthly: $17.40\n\nSavings: $27.60/month (61%)"
      },
      {
        "title": "Example 2: Customer Support",
        "body": "Without Smart Router:\n- 500 requests/day to GPT-4\n- Monthly: $300\n\nWith Smart Router:\n- 400 to GPT-3.5 ($24)\n- 80 to GPT-4-Turbo ($24)\n- 20 to GPT-4 ($12)\n- Monthly: $60\n\nSavings: $240/month (80%)"
      },
      {
        "title": "Agent Economy",
        "body": "Agents can autonomously evaluate if Pro tier is worth it:\n\nCost: 0.5 USDT/month\nValue: Saves 30-50% on model costs\nROI: If saves >0.5 USDT/month, it pays for itself\n\nExample ROI:\n\nAgent making 100 requests/day:\n- Without router: $45/month\n- With router: $17.40/month\n- Savings: $27.60/month\n- Pro cost: $0.50/month\n- Net profit: $27.10/month\n- ROI: 5,420%\n\nEconomic rationale: If routing decisions save more than 0.5 USDT/month in model costs, Pro tier pays for itself. Agent can autonomously pay via x402 without human approval.\n\nSee AGENT-PAYMENTS.md for x402 integration details."
      },
      {
        "title": "Pattern Learning",
        "body": "Smart Router learns from your usage:\n\nExample Learning:\n\nPattern detected: \"Debug Python errors\"\nHistory: Haiku failed 3 times, Sonnet succeeded 5 times\nLearning: Always use Sonnet+ for Python debugging\n\nNext time: \"Debug this Python error...\"\n→ Automatically routes to Sonnet instead of Haiku\n\nWhat it learns:\n\nTask-based patterns (debugging, refactoring, writing)\nComplexity patterns (what works at different levels)\nBudget patterns (when to downgrade, when quality matters)\nProvider patterns (which providers work best for your tasks)"
      },
      {
        "title": "Memory System",
        "body": "Stores routing patterns as persistent memories\nRecalls successful model selections across sessions\nMaximum learning efficiency"
      },
      {
        "title": "Context Optimizer",
        "body": "Combine for 60-80% total cost reduction\nCompress context (40-60% token savings)\nRoute to cheaper model (30-50% cost savings)\nTogether = maximum efficiency"
      },
      {
        "title": "Cost Governor",
        "body": "Smart Router optimizes model selection\nCost Governor enforces hard spending limits\nTogether = maximum cost control\n\n# Install full efficiency suite\nclaw skill install openclaw-memory\nclaw skill install openclaw-context-optimizer\nclaw skill install openclaw-smart-router"
      },
      {
        "title": "Privacy",
        "body": "All data stored locally in ~/.openclaw/openclaw-smart-router/\nNo external servers or telemetry\nRouting happens locally (no API calls)\nOpen source - audit the code yourself"
      },
      {
        "title": "Dashboard",
        "body": "Access web UI at http://localhost:9093:\n\nReal-time routing decisions\nComplexity distribution chart\nModel selection breakdown\nCost savings over time\nROI calculation\nPattern learning insights\nBudget tracking\nLicense status"
      },
      {
        "title": "ROI Tracking",
        "body": "Smart Router automatically calculates return on investment:\n\n$ claw router savings\n\nCost Analysis (Last 30 Days)\n────────────────────────────────\nRouting decisions: 2,847\nAverage complexity: 0.45\n\nModel distribution:\n- Haiku: 42% ($3.60)\n- Sonnet: 49% ($21.00)\n- Opus: 9% ($11.12)\n\nTotal actual cost: $35.72\nWithout Smart Router: $128.12\nSavings: $92.40 (72%)\n\nPro cost: $0.50/month\nNet profit: $91.90/month\nROI: 18,380% 🎉"
      },
      {
        "title": "Requirements",
        "body": "Node.js 18+\nOpenClaw v2026.1.30+\nOS: Windows, macOS, Linux\nOptional: OpenClaw Memory System (recommended)\nOptional: OpenClaw Context Optimizer (highly recommended)"
      },
      {
        "title": "API Reference",
        "body": "# Analyze complexity\nPOST /api/analyze\n{\n  \"agent_wallet\": \"0x...\",\n  \"query\": \"Task description...\",\n  \"context_length\": 1500\n}\n\n# Response:\n{\n  \"complexity\": 0.65,\n  \"recommended_model\": \"claude-sonnet-4-5\",\n  \"recommended_provider\": \"anthropic\",\n  \"estimated_cost\": 0.008,\n  \"reasoning\": \"Medium complexity code task\"\n}\n\n# Get routing stats\nGET /api/stats?agent_wallet=0x...\n\n# Get savings analysis\nGET /api/savings?agent_wallet=0x...\n\n# Get learned patterns\nGET /api/patterns?agent_wallet=0x...\n\n# x402 payment endpoints\nPOST /api/x402/subscribe\nPOST /api/x402/verify\nGET /api/x402/license/:wallet"
      },
      {
        "title": "Budget Awareness",
        "body": "Smart Router respects your spending limits:\n\nBudget levels:\n\nPer-request max ($0.50 default)\nDaily limit ($5.00 default)\nMonthly limit ($100.00 default)\n\nBudget strategies:\n\nConservative: Prefer cheaper models when viable\nBalanced: Use recommended model, respect hard limits\nQuality-First: Prioritize best model, soft budget constraints\n\nBudget constraint handling:\n\nIF daily_limit_reached:\n  → Downgrade to cheapest viable model\n  → Warn user about constraint\n  → Log budget event"
      },
      {
        "title": "Supported Models",
        "body": "Anthropic:\n\nclaude-haiku-4-5 (simple)\nclaude-sonnet-4-5 (medium)\nclaude-opus-4-5 (complex)\n\nOpenAI:\n\ngpt-3.5-turbo (simple)\ngpt-4-turbo (medium)\ngpt-4 (complex)\n\nGoogle:\n\ngemini-1.5-flash (simple)\ngemini-1.5-pro (medium/complex)\n\nCustom providers:\n\nEasily configure your own models and costs"
      },
      {
        "title": "Statistics Example",
        "body": "Smart Router Stats (30 Days)\n────────────────────────────────\nTotal decisions: 2,847\nAvg complexity: 0.45\n\nComplexity breakdown:\n- Simple (0.0-0.3): 42%\n- Medium (0.3-0.6): 37%\n- Complex (0.6-0.8): 15%\n- Expert (0.8-1.0): 6%\n\nModel distribution:\n- Haiku: 1,200 (42%)\n- Sonnet: 1,400 (49%)\n- Opus: 247 (9%)\n\nCost: $35.72 (vs $128.12 without)\nSavings: 72% ($92.40/month)\n\nPattern learning:\n- 23 patterns identified\n- 94% success rate\n- 342 pattern applications"
      },
      {
        "title": "Economic Rationale",
        "body": "Should you upgrade to Pro?\n\nCalculate your potential savings:\n\nCurrent requests/day × Avg cost per request = Monthly cost\nApply 30-50% savings = Amount saved\nIf saved amount > 0.5 USDT/month → Pro pays for itself\n\nTypical savings:\n\nLight usage (10-20 req/day): $3-8/month → $2.50-7.50 profit\nMedium usage (50-100 req/day): $20-45/month → $19.50-44.50 profit\nHeavy usage (200+ req/day): $100+/month → $99.50+ profit\n\nROI gets better with scale."
      },
      {
        "title": "Links",
        "body": "Full Documentation\nRouting Guide\nAgent Payments Guide\nGitHub Repository\nClawHub Page\n\nBuilt by the OpenClaw community | First smart model router with x402 payments"
      }
    ],
    "body": "OpenClaw Smart Router\n\nSave 30-50% on model costs through intelligent, automatic model selection.\n\nWhat is it?\n\nThe first OpenClaw skill that automatically routes requests to optimal models based on complexity analysis and budget constraints. Stops you from wasting money on expensive models for simple tasks. Learns from your usage patterns and gets smarter over time.\n\nKey Features\n🎯 30-50% Cost Savings - Automatic model selection based on task complexity\n🧠 Complexity Analysis - Scores tasks 0.0-1.0 and selects appropriate model\n💰 Budget Awareness - Respects spending limits and cost targets\n📊 Pattern Learning - Learns which models work best for your tasks\n🔄 Multi-Provider - Works with Anthropic, OpenAI, Google, and more\n💸 x402 Payments - Agents can pay for unlimited routing (0.5 USDT/month)\nFree vs Pro Tier\n\nFree Tier:\n\n100 routing decisions per day\nAutomatic complexity analysis\nBasic model selection\nCost tracking\n\nPro Tier (0.5 USDT/month):\n\nUnlimited routing decisions\nAdvanced pattern learning\nCustom routing rules\nDetailed analytics and ROI tracking\nBudget optimization\nInstallation\nclaw skill install openclaw-smart-router\n\nCommands\n# View routing stats\nclaw router stats\n\n# Analyze complexity\nclaw router analyze \"Your task description...\"\n\n# View routing history\nclaw router history --limit=10\n\n# Show cost savings\nclaw router savings\n\n# Open dashboard\nclaw router dashboard\n\n# Subscribe to Pro\nclaw router subscribe\n\nHow It Works\nIntercepts requests - Hooks before each API call\nAnalyzes complexity - Scores task from 0.0 (simple) to 1.0 (expert)\nChecks budget - Considers spending limits\nSelects model - Chooses optimal model:\nSimple (0.0-0.3) → Haiku/GPT-3.5\nMedium (0.3-0.6) → Sonnet/GPT-4-Turbo\nComplex (0.6-0.8) → Opus/GPT-4\nExpert (0.8-1.0) → Opus/GPT-4\nRoutes request - Sends to selected model\nLearns from result - Tracks success and adapts\nComplexity Scoring\n\nWhat makes a task complex?\n\nContext length (more context = higher complexity)\nCode presence (code analysis scores higher)\nError messages (debugging is complex)\nTask type (writing < coding < reasoning < research)\nQuestion complexity (multiple parts, nested logic)\nSpecificity (vague requests need stronger models)\n\nExamples:\n\nSimple (0.0-0.3) → Haiku:\n\n\"What's the current time?\"\n\"Format this JSON\"\n\"Fix typo in variable name\"\n\nMedium (0.3-0.6) → Sonnet:\n\n\"Refactor this class to use interfaces\"\n\"Write unit tests for this function\"\n\"Explain how React hooks work\"\n\nComplex (0.6-0.8) → Opus:\n\n\"Debug this multi-threaded race condition\"\n\"Design a scalable caching strategy\"\n\"Optimize this algorithm for performance\"\n\nExpert (0.8-1.0) → Opus:\n\n\"Design a distributed system architecture\"\n\"Solve this novel algorithmic problem\"\n\"Research and synthesize from multiple sources\"\nUse Cases\nReduce model costs by 30-50% automatically\nStop manually switching between models\nBudget-aware routing for cost control\nLearn optimal model selection from patterns\nTrack spending and ROI over time\nCost Savings Examples\nExample 1: Development Work\nWithout Smart Router:\n- 100 requests/day to Opus\n- $0.015 per request\n- Monthly: $45\n\nWith Smart Router:\n- 30 requests to Haiku ($0.90)\n- 50 requests to Sonnet ($7.50)\n- 20 requests to Opus ($9.00)\n- Monthly: $17.40\n\nSavings: $27.60/month (61%)\n\nExample 2: Customer Support\nWithout Smart Router:\n- 500 requests/day to GPT-4\n- Monthly: $300\n\nWith Smart Router:\n- 400 to GPT-3.5 ($24)\n- 80 to GPT-4-Turbo ($24)\n- 20 to GPT-4 ($12)\n- Monthly: $60\n\nSavings: $240/month (80%)\n\nAgent Economy\n\nAgents can autonomously evaluate if Pro tier is worth it:\n\nCost: 0.5 USDT/month\nValue: Saves 30-50% on model costs\nROI: If saves >0.5 USDT/month, it pays for itself\n\nExample ROI:\n\nAgent making 100 requests/day:\n- Without router: $45/month\n- With router: $17.40/month\n- Savings: $27.60/month\n- Pro cost: $0.50/month\n- Net profit: $27.10/month\n- ROI: 5,420%\n\n\nEconomic rationale: If routing decisions save more than 0.5 USDT/month in model costs, Pro tier pays for itself. Agent can autonomously pay via x402 without human approval.\n\nSee AGENT-PAYMENTS.md for x402 integration details.\n\nPattern Learning\n\nSmart Router learns from your usage:\n\nExample Learning:\n\nPattern detected: \"Debug Python errors\"\nHistory: Haiku failed 3 times, Sonnet succeeded 5 times\nLearning: Always use Sonnet+ for Python debugging\n\nNext time: \"Debug this Python error...\"\n→ Automatically routes to Sonnet instead of Haiku\n\n\nWhat it learns:\n\nTask-based patterns (debugging, refactoring, writing)\nComplexity patterns (what works at different levels)\nBudget patterns (when to downgrade, when quality matters)\nProvider patterns (which providers work best for your tasks)\nIntegration with Other Tools\nMemory System\nStores routing patterns as persistent memories\nRecalls successful model selections across sessions\nMaximum learning efficiency\nContext Optimizer\nCombine for 60-80% total cost reduction\nCompress context (40-60% token savings)\nRoute to cheaper model (30-50% cost savings)\nTogether = maximum efficiency\nCost Governor\nSmart Router optimizes model selection\nCost Governor enforces hard spending limits\nTogether = maximum cost control\n# Install full efficiency suite\nclaw skill install openclaw-memory\nclaw skill install openclaw-context-optimizer\nclaw skill install openclaw-smart-router\n\nPrivacy\nAll data stored locally in ~/.openclaw/openclaw-smart-router/\nNo external servers or telemetry\nRouting happens locally (no API calls)\nOpen source - audit the code yourself\nDashboard\n\nAccess web UI at http://localhost:9093:\n\nReal-time routing decisions\nComplexity distribution chart\nModel selection breakdown\nCost savings over time\nROI calculation\nPattern learning insights\nBudget tracking\nLicense status\nROI Tracking\n\nSmart Router automatically calculates return on investment:\n\n$ claw router savings\n\nCost Analysis (Last 30 Days)\n────────────────────────────────\nRouting decisions: 2,847\nAverage complexity: 0.45\n\nModel distribution:\n- Haiku: 42% ($3.60)\n- Sonnet: 49% ($21.00)\n- Opus: 9% ($11.12)\n\nTotal actual cost: $35.72\nWithout Smart Router: $128.12\nSavings: $92.40 (72%)\n\nPro cost: $0.50/month\nNet profit: $91.90/month\nROI: 18,380% 🎉\n\nRequirements\nNode.js 18+\nOpenClaw v2026.1.30+\nOS: Windows, macOS, Linux\nOptional: OpenClaw Memory System (recommended)\nOptional: OpenClaw Context Optimizer (highly recommended)\nAPI Reference\n# Analyze complexity\nPOST /api/analyze\n{\n  \"agent_wallet\": \"0x...\",\n  \"query\": \"Task description...\",\n  \"context_length\": 1500\n}\n\n# Response:\n{\n  \"complexity\": 0.65,\n  \"recommended_model\": \"claude-sonnet-4-5\",\n  \"recommended_provider\": \"anthropic\",\n  \"estimated_cost\": 0.008,\n  \"reasoning\": \"Medium complexity code task\"\n}\n\n# Get routing stats\nGET /api/stats?agent_wallet=0x...\n\n# Get savings analysis\nGET /api/savings?agent_wallet=0x...\n\n# Get learned patterns\nGET /api/patterns?agent_wallet=0x...\n\n# x402 payment endpoints\nPOST /api/x402/subscribe\nPOST /api/x402/verify\nGET /api/x402/license/:wallet\n\nBudget Awareness\n\nSmart Router respects your spending limits:\n\nBudget levels:\n\nPer-request max ($0.50 default)\nDaily limit ($5.00 default)\nMonthly limit ($100.00 default)\n\nBudget strategies:\n\nConservative: Prefer cheaper models when viable\nBalanced: Use recommended model, respect hard limits\nQuality-First: Prioritize best model, soft budget constraints\n\nBudget constraint handling:\n\nIF daily_limit_reached:\n  → Downgrade to cheapest viable model\n  → Warn user about constraint\n  → Log budget event\n\nSupported Models\n\nAnthropic:\n\nclaude-haiku-4-5 (simple)\nclaude-sonnet-4-5 (medium)\nclaude-opus-4-5 (complex)\n\nOpenAI:\n\ngpt-3.5-turbo (simple)\ngpt-4-turbo (medium)\ngpt-4 (complex)\n\nGoogle:\n\ngemini-1.5-flash (simple)\ngemini-1.5-pro (medium/complex)\n\nCustom providers:\n\nEasily configure your own models and costs\nStatistics Example\nSmart Router Stats (30 Days)\n────────────────────────────────\nTotal decisions: 2,847\nAvg complexity: 0.45\n\nComplexity breakdown:\n- Simple (0.0-0.3): 42%\n- Medium (0.3-0.6): 37%\n- Complex (0.6-0.8): 15%\n- Expert (0.8-1.0): 6%\n\nModel distribution:\n- Haiku: 1,200 (42%)\n- Sonnet: 1,400 (49%)\n- Opus: 247 (9%)\n\nCost: $35.72 (vs $128.12 without)\nSavings: 72% ($92.40/month)\n\nPattern learning:\n- 23 patterns identified\n- 94% success rate\n- 342 pattern applications\n\nEconomic Rationale\n\nShould you upgrade to Pro?\n\nCalculate your potential savings:\n\nCurrent requests/day × Avg cost per request = Monthly cost\nApply 30-50% savings = Amount saved\nIf saved amount > 0.5 USDT/month → Pro pays for itself\n\n\nTypical savings:\n\nLight usage (10-20 req/day): $3-8/month → $2.50-7.50 profit\nMedium usage (50-100 req/day): $20-45/month → $19.50-44.50 profit\nHeavy usage (200+ req/day): $100+/month → $99.50+ profit\n\nROI gets better with scale.\n\nLinks\nFull Documentation\nRouting Guide\nAgent Payments Guide\nGitHub Repository\nClawHub Page\n\nBuilt by the OpenClaw community | First smart model router with x402 payments"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AtlasPA/openclaw-smart-router",
    "publisherUrl": "https://clawhub.ai/AtlasPA/openclaw-smart-router",
    "owner": "AtlasPA",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-smart-router",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-smart-router",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-smart-router/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-smart-router/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-smart-router/agent.md"
  }
}