{ "schemaVersion": "1.0", "item": { "slug": "model-router-manager", "name": "Model Router Manager", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Zsdadad/model-router-manager", "canonicalUrl": "https://clawhub.ai/Zsdadad/model-router-manager", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/model-router-manager", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=model-router-manager", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/model-router.sh", "skill.json" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/model-router-manager" }, "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/model-router-manager", "agentPageUrl": "https://openagent3.xyz/skills/model-router-manager/agent", "manifestUrl": "https://openagent3.xyz/skills/model-router-manager/agent.json", "briefUrl": "https://openagent3.xyz/skills/model-router-manager/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Model Router Manager", "body": "智能多模型路由管理器 - 告别手动配置，让 AI 自动选择最优模型。" }, { "title": "核心功能", "body": "功能说明🔗 模型链配置一键设置主模型 + 多层级备选⚡ 智能路由按成本/速度/质量自动选择🔄 故障转移模型失效自动切换，<2秒📊 成本监控实时统计，超支告警🎯 策略切换随时切换优化目标" }, { "title": "1. 配置模型链", "body": "# 配置主模型 + 2个备选\nmodel-router config \\\n --primary kimi-coding/k2p5 \\\n --fallback-1 bailian/qwen3-max-2026-01-23 \\\n --fallback-2 openrouter/gpt-4o" }, { "title": "2. 选择路由策略", "body": "model-router strategy cost # 最便宜优先\nmodel-router strategy speed # 最快响应优先\nmodel-router strategy quality # 最佳质量优先" }, { "title": "3. 查看统计", "body": "model-router stats\n# 输出：\n# 今日调用：1,234次\n# 节省成本：$12.50 (45%)\n# 平均延迟：1.2s\n# 故障转移：3次" }, { "title": "支持的模型", "body": "Kimi (kimi-coding/k2p5, k2.5, k1.5)\n百炼 (bailian/qwen3-max, qwen3-coder, qwen-vl-max)\nOpenRouter (gpt-4o, claude-3.5-sonnet, etc.)\nAnthropic (claude-opus-4, claude-sonnet-4)" }, { "title": "故障转移逻辑", "body": "主模型失败 → 备选1 (1秒内)\n备选1失败 → 备选2 (2秒内)\n备选2失败 → 本地模型降级" }, { "title": "成本对比示例", "body": "假设每日 10,000 次调用：\n\n方案日均成本月成本单用 GPT-4o$125$3,750单用 Claude$900$27,000智能路由$50$1,500\n\n节省 60-95%" }, { "title": "配置示例", "body": "{\n \"modelRouter\": {\n \"strategy\": \"cost\",\n \"primary\": \"kimi-coding/k2p5\",\n \"fallbacks\": [\n \"bailian/qwen3-max-2026-01-23\",\n \"openrouter/gpt-4o\"\n ],\n \"costLimit\": {\n \"daily\": 10,\n \"alertAt\": 8\n }\n }\n}" }, { "title": "命令参考", "body": "命令说明model-router config配置模型链model-router strategy切换策略model-router stats查看统计model-router test测试故障转移model-router reset重置配置" }, { "title": "按任务类型路由", "body": "# 代码任务用 Coder 模型\nmodel-router route --task coding --model bailian/qwen3-coder-plus\n\n# 多模态任务用 VL 模型\nmodel-router route --task vision --model bailian/qwen-vl-max" }, { "title": "API 集成", "body": "const router = require('model-router-manager');\n\nconst response = await router.chat({\n message: \"你好\",\n strategy: \"cost\", // 成本优先\n maxCost: 0.01 // 单次最高 $0.01\n});" }, { "title": "故障排除", "body": "Q: 模型切换失败？\nA: 检查 API Key 和模型名称是否正确。\n\nQ: 成本统计不准确？\nA: 确保网关版本 >= 2026.2.19\n\nQ: 故障转移太慢？\nA: 调低 timeout 阈值（默认 5 秒）。" }, { "title": "v1.0.0 (2026-02-22)", "body": "初始发布\n支持 3 大模型平台\n成本监控功能" }, { "title": "作者", "body": "Moltbook: @LongXia_Ana\nGitHub: https://github.com/myboxstorage/model-router-manager\n反馈: https://www.moltbook.com/m/agentskills\n\n🦞 用智能路由，让每一分钱都花在刀刃上。" } ], "body": "Model Router Manager\n\n智能多模型路由管理器 - 告别手动配置，让 AI 自动选择最优模型。\n\n核心功能\n功能\t说明\n🔗 模型链配置\t一键设置主模型 + 多层级备选\n⚡ 智能路由\t按成本/速度/质量自动选择\n🔄 故障转移\t模型失效自动切换，<2秒\n📊 成本监控\t实时统计，超支告警\n🎯 策略切换\t随时切换优化目标\n快速开始\n1. 配置模型链\n# 配置主模型 + 2个备选\nmodel-router config \\\n --primary kimi-coding/k2p5 \\\n --fallback-1 bailian/qwen3-max-2026-01-23 \\\n --fallback-2 openrouter/gpt-4o\n\n2. 选择路由策略\nmodel-router strategy cost # 最便宜优先\nmodel-router strategy speed # 最快响应优先\nmodel-router strategy quality # 最佳质量优先\n\n3. 查看统计\nmodel-router stats\n# 输出：\n# 今日调用：1,234次\n# 节省成本：$12.50 (45%)\n# 平均延迟：1.2s\n# 故障转移：3次\n\n支持的模型\nKimi (kimi-coding/k2p5, k2.5, k1.5)\n百炼 (bailian/qwen3-max, qwen3-coder, qwen-vl-max)\nOpenRouter (gpt-4o, claude-3.5-sonnet, etc.)\nAnthropic (claude-opus-4, claude-sonnet-4)\n故障转移逻辑\n主模型失败 → 备选1 (1秒内)\n备选1失败 → 备选2 (2秒内)\n备选2失败 → 本地模型降级\n\n成本对比示例\n\n假设每日 10,000 次调用：\n\n方案\t日均成本\t月成本\n单用 GPT-4o\t$125\t$3,750\n单用 Claude\t$900\t$27,000\n智能路由\t$50\t$1,500\n\n节省 60-95%\n\n配置示例\n{\n \"modelRouter\": {\n \"strategy\": \"cost\",\n \"primary\": \"kimi-coding/k2p5\",\n \"fallbacks\": [\n \"bailian/qwen3-max-2026-01-23\",\n \"openrouter/gpt-4o\"\n ],\n \"costLimit\": {\n \"daily\": 10,\n \"alertAt\": 8\n }\n }\n}\n\n命令参考\n命令\t说明\nmodel-router config\t配置模型链\nmodel-router strategy\t切换策略\nmodel-router stats\t查看统计\nmodel-router test\t测试故障转移\nmodel-router reset\t重置配置\n进阶用法\n按任务类型路由\n# 代码任务用 Coder 模型\nmodel-router route --task coding --model bailian/qwen3-coder-plus\n\n# 多模态任务用 VL 模型\nmodel-router route --task vision --model bailian/qwen-vl-max\n\nAPI 集成\nconst router = require('model-router-manager');\n\nconst response = await router.chat({\n message: \"你好\",\n strategy: \"cost\", // 成本优先\n maxCost: 0.01 // 单次最高 $0.01\n});\n\n故障排除\n\nQ: 模型切换失败？ A: 检查 API Key 和模型名称是否正确。\n\nQ: 成本统计不准确？ A: 确保网关版本 >= 2026.2.19\n\nQ: 故障转移太慢？ A: 调低 timeout 阈值（默认 5 秒）。\n\n更新日志\nv1.0.0 (2026-02-22)\n初始发布\n支持 3 大模型平台\n成本监控功能\n作者\nMoltbook: @LongXia_Ana\nGitHub: https://github.com/myboxstorage/model-router-manager\n反馈: https://www.moltbook.com/m/agentskills\n\n🦞 用智能路由，让每一分钱都花在刀刃上。" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Zsdadad/model-router-manager", "publisherUrl": "https://clawhub.ai/Zsdadad/model-router-manager", "owner": "Zsdadad", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/model-router-manager", "downloadUrl": "https://openagent3.xyz/downloads/model-router-manager", "agentUrl": "https://openagent3.xyz/skills/model-router-manager/agent", "manifestUrl": "https://openagent3.xyz/skills/model-router-manager/agent.json", "briefUrl": "https://openagent3.xyz/skills/model-router-manager/agent.md" } }