{ "schemaVersion": "1.0", "item": { "slug": "chinese-llm-router", "name": "Chinese LLM Router", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Xdd-xund/chinese-llm-router", "canonicalUrl": "https://clawhub.ai/Xdd-xund/chinese-llm-router", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/chinese-llm-router", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=chinese-llm-router", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/api-reference.md", "scripts/router.js", "scripts/setup.js" ], "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/chinese-llm-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/chinese-llm-router", "agentPageUrl": "https://openagent3.xyz/skills/chinese-llm-router/agent", "manifestUrl": "https://openagent3.xyz/skills/chinese-llm-router/agent.json", "briefUrl": "https://openagent3.xyz/skills/chinese-llm-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": "Chinese LLM Router", "body": "Route your OpenClaw conversations to the best Chinese AI models — no config headaches, just pick and chat." }, { "title": "What It Does", "body": "Gives your OpenClaw instant access to all major Chinese LLMs through a single unified interface:\n\nDeepSeek (V3.2 / R1) — Best open-source reasoning, dirt cheap\nQwen (Qwen3-Max / Qwen3-Max-Thinking / Qwen3-Coder-Plus) — Alibaba's flagship, strong all-rounder\nGLM (GLM-5 / GLM-4.7) — Zhipu AI, top-tier coding & agent tasks\nKimi (K2.5 / K2.5-Thinking) — Moonshot AI, great for long context & vision\nDoubao Seed 2.0 (Pro / Lite / Mini) — ByteDance, fast & cheap\nMiniMax (M2.5) — Lightweight powerhouse, runs locally too\nStep (3.5 Flash) — StepFun, blazing fast inference\nBaichuan (Baichuan4-Turbo) — Strong Chinese language understanding\nSpark (v4.0 Ultra) — iFlytek, speech & Chinese NLP specialist\nHunyuan (Turbo-S) — Tencent, WeChat ecosystem integration" }, { "title": "Quick Start", "body": "Tell your OpenClaw:\n\nUse DeepSeek V3.2 for this conversation\n\nOr ask it to pick the best model:\n\nWhich Chinese model is best for coding? Switch to it." }, { "title": "Commands", "body": "CommandWhat it doeslist modelsShow all available Chinese LLMs with statususe Switch to a specific modelcompare Compare capabilities & pricingrecommend Get model recommendation for a task typetest Send a test prompt to verify connectivitystatusCheck which models are currently accessible" }, { "title": "Model Selection Guide", "body": "TaskRecommended ModelWhyGeneral chatQwen3-MaxBest all-rounder, strong ChineseCodingGLM-5 / Kimi K2.5Top coding benchmarksMath & reasoningDeepSeek R1Purpose-built for reasoningLong documentsKimi K2.5 (128K) / DeepSeek V3.2 (1M)Massive context windowsFast & cheapStep 3.5 Flash / Doubao Seed 2.0 MiniSub-second latencyCreative writingQwen3-Max / Doubao Seed 2.0 ProRich Chinese expressionAgent tasksGLM-5 / Qwen3-MaxBest tool-use support" }, { "title": "Configuration", "body": "The skill reads API keys from environment or from ~/.chinese-llm-router/config.json:\n\n{\n \"providers\": {\n \"deepseek\": {\n \"apiKey\": \"sk-xxx\",\n \"baseUrl\": \"https://api.deepseek.com/v1\",\n \"models\": [\"deepseek-chat\", \"deepseek-reasoner\"]\n },\n \"qwen\": {\n \"apiKey\": \"sk-xxx\",\n \"baseUrl\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n \"models\": [\"qwen3-max\", \"qwen3-max-thinking\", \"qwen3-coder-plus\"]\n },\n \"glm\": {\n \"apiKey\": \"xxx.xxx\",\n \"baseUrl\": \"https://open.bigmodel.cn/api/paas/v4\",\n \"models\": [\"glm-5\", \"glm-4-plus\"]\n },\n \"kimi\": {\n \"apiKey\": \"sk-xxx\",\n \"baseUrl\": \"https://api.moonshot.cn/v1\",\n \"models\": [\"kimi-k2.5\", \"kimi-k2.5-thinking\"]\n },\n \"doubao\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://ark.cn-beijing.volces.com/api/v3\",\n \"models\": [\"doubao-seed-2.0-pro\", \"doubao-seed-2.0-lite\", \"doubao-seed-2.0-mini\"]\n },\n \"minimax\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.minimax.chat/v1\",\n \"models\": [\"minimax-m2.5\"]\n },\n \"step\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.stepfun.com/v1\",\n \"models\": [\"step-3.5-flash\"]\n },\n \"baichuan\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.baichuan-ai.com/v1\",\n \"models\": [\"baichuan4-turbo\"]\n },\n \"spark\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://spark-api-open.xf-yun.com/v1\",\n \"models\": [\"spark-v4.0-ultra\"]\n },\n \"hunyuan\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.hunyuan.cloud.tencent.com/v1\",\n \"models\": [\"hunyuan-turbo-s\"]\n }\n },\n \"default\": \"qwen3-max\",\n \"fallback\": [\"deepseek-chat\", \"doubao-seed-2.0-pro\"]\n}" }, { "title": "Setup", "body": "Get API keys from the providers you want (most offer free tiers):\n\nDeepSeek: https://platform.deepseek.com\nQwen (Alibaba): https://dashscope.console.aliyun.com\nGLM (Zhipu): https://open.bigmodel.cn\nKimi (Moonshot): https://platform.moonshot.cn\nDoubao (ByteDance): https://console.volcengine.com/ark\nMiniMax: https://platform.minimaxi.com\nStep (StepFun): https://platform.stepfun.com\nBaichuan: https://platform.baichuan-ai.com\nSpark (iFlytek): https://console.xfyun.cn\nHunyuan (Tencent): https://cloud.tencent.com/product/hunyuan\n\n\n\nRun the setup script:\nnode scripts/setup.js\n\n\n\nDone! Your OpenClaw can now use any configured model." }, { "title": "Pricing Reference (Feb 2026)", "body": "ModelInput (¥/M tokens)Output (¥/M tokens)NotesDeepSeek V3.2¥0.5 (cache ¥0.1)¥2.0Cheapest flagshipQwen3-Max¥2.0¥6.0Free tier availableGLM-5¥5.0¥5.0Just launched, may changeKimi K2.5¥2.0¥6.0Open source, self-host freeDoubao Seed 2.0 Pro¥0.8¥2.0ByteDance subsidyDoubao Seed 2.0 Mini¥0.15¥0.3Ultra cheapMiniMax M2.5¥1.0¥3.0Can run locallyStep 3.5 Flash¥0.7¥1.4Fastest inference\n\nPrices as of Feb 2026. All providers offer free tiers or credits for new users." }, { "title": "All APIs are OpenAI-Compatible", "body": "Every provider listed uses the OpenAI chat/completions format. No special SDKs needed — just change baseUrl and apiKey." }, { "title": "Features", "body": "Auto-fallback: If one provider is down, automatically try the next\nCost tracking: See per-model token usage and estimated cost\nSmart routing: Describe your task, get the best model recommendation\nBatch compare: Send the same prompt to multiple models, compare outputs\nContext-aware: Remembers your model preference per conversation topic" }, { "title": "Links", "body": "🦐 Try our AI Plaza: https://ai.xudd-v.com\n📦 ClawHub: https://clawhub.ai/Xdd-xund/chinese-llm-router\n💬 Feedback: https://ai.xudd-v.com/connect.html" } ], "body": "Chinese LLM Router\n\nRoute your OpenClaw conversations to the best Chinese AI models — no config headaches, just pick and chat.\n\nWhat It Does\n\nGives your OpenClaw instant access to all major Chinese LLMs through a single unified interface:\n\nDeepSeek (V3.2 / R1) — Best open-source reasoning, dirt cheap\nQwen (Qwen3-Max / Qwen3-Max-Thinking / Qwen3-Coder-Plus) — Alibaba's flagship, strong all-rounder\nGLM (GLM-5 / GLM-4.7) — Zhipu AI, top-tier coding & agent tasks\nKimi (K2.5 / K2.5-Thinking) — Moonshot AI, great for long context & vision\nDoubao Seed 2.0 (Pro / Lite / Mini) — ByteDance, fast & cheap\nMiniMax (M2.5) — Lightweight powerhouse, runs locally too\nStep (3.5 Flash) — StepFun, blazing fast inference\nBaichuan (Baichuan4-Turbo) — Strong Chinese language understanding\nSpark (v4.0 Ultra) — iFlytek, speech & Chinese NLP specialist\nHunyuan (Turbo-S) — Tencent, WeChat ecosystem integration\nQuick Start\n\nTell your OpenClaw:\n\nUse DeepSeek V3.2 for this conversation\n\n\nOr ask it to pick the best model:\n\nWhich Chinese model is best for coding? Switch to it.\n\nCommands\nCommand\tWhat it does\nlist models\tShow all available Chinese LLMs with status\nuse \tSwitch to a specific model\ncompare \tCompare capabilities & pricing\nrecommend \tGet model recommendation for a task type\ntest \tSend a test prompt to verify connectivity\nstatus\tCheck which models are currently accessible\nModel Selection Guide\nTask\tRecommended Model\tWhy\nGeneral chat\tQwen3-Max\tBest all-rounder, strong Chinese\nCoding\tGLM-5 / Kimi K2.5\tTop coding benchmarks\nMath & reasoning\tDeepSeek R1\tPurpose-built for reasoning\nLong documents\tKimi K2.5 (128K) / DeepSeek V3.2 (1M)\tMassive context windows\nFast & cheap\tStep 3.5 Flash / Doubao Seed 2.0 Mini\tSub-second latency\nCreative writing\tQwen3-Max / Doubao Seed 2.0 Pro\tRich Chinese expression\nAgent tasks\tGLM-5 / Qwen3-Max\tBest tool-use support\nConfiguration\n\nThe skill reads API keys from environment or from ~/.chinese-llm-router/config.json:\n\n{\n \"providers\": {\n \"deepseek\": {\n \"apiKey\": \"sk-xxx\",\n \"baseUrl\": \"https://api.deepseek.com/v1\",\n \"models\": [\"deepseek-chat\", \"deepseek-reasoner\"]\n },\n \"qwen\": {\n \"apiKey\": \"sk-xxx\",\n \"baseUrl\": \"https://dashscope.aliyuncs.com/compatible-mode/v1\",\n \"models\": [\"qwen3-max\", \"qwen3-max-thinking\", \"qwen3-coder-plus\"]\n },\n \"glm\": {\n \"apiKey\": \"xxx.xxx\",\n \"baseUrl\": \"https://open.bigmodel.cn/api/paas/v4\",\n \"models\": [\"glm-5\", \"glm-4-plus\"]\n },\n \"kimi\": {\n \"apiKey\": \"sk-xxx\",\n \"baseUrl\": \"https://api.moonshot.cn/v1\",\n \"models\": [\"kimi-k2.5\", \"kimi-k2.5-thinking\"]\n },\n \"doubao\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://ark.cn-beijing.volces.com/api/v3\",\n \"models\": [\"doubao-seed-2.0-pro\", \"doubao-seed-2.0-lite\", \"doubao-seed-2.0-mini\"]\n },\n \"minimax\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.minimax.chat/v1\",\n \"models\": [\"minimax-m2.5\"]\n },\n \"step\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.stepfun.com/v1\",\n \"models\": [\"step-3.5-flash\"]\n },\n \"baichuan\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.baichuan-ai.com/v1\",\n \"models\": [\"baichuan4-turbo\"]\n },\n \"spark\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://spark-api-open.xf-yun.com/v1\",\n \"models\": [\"spark-v4.0-ultra\"]\n },\n \"hunyuan\": {\n \"apiKey\": \"xxx\",\n \"baseUrl\": \"https://api.hunyuan.cloud.tencent.com/v1\",\n \"models\": [\"hunyuan-turbo-s\"]\n }\n },\n \"default\": \"qwen3-max\",\n \"fallback\": [\"deepseek-chat\", \"doubao-seed-2.0-pro\"]\n}\n\nSetup\n\nGet API keys from the providers you want (most offer free tiers):\n\nDeepSeek: https://platform.deepseek.com\nQwen (Alibaba): https://dashscope.console.aliyun.com\nGLM (Zhipu): https://open.bigmodel.cn\nKimi (Moonshot): https://platform.moonshot.cn\nDoubao (ByteDance): https://console.volcengine.com/ark\nMiniMax: https://platform.minimaxi.com\nStep (StepFun): https://platform.stepfun.com\nBaichuan: https://platform.baichuan-ai.com\nSpark (iFlytek): https://console.xfyun.cn\nHunyuan (Tencent): https://cloud.tencent.com/product/hunyuan\n\nRun the setup script:\n\nnode scripts/setup.js\n\n\nDone! Your OpenClaw can now use any configured model.\n\nPricing Reference (Feb 2026)\nModel\tInput (¥/M tokens)\tOutput (¥/M tokens)\tNotes\nDeepSeek V3.2\t¥0.5 (cache ¥0.1)\t¥2.0\tCheapest flagship\nQwen3-Max\t¥2.0\t¥6.0\tFree tier available\nGLM-5\t¥5.0\t¥5.0\tJust launched, may change\nKimi K2.5\t¥2.0\t¥6.0\tOpen source, self-host free\nDoubao Seed 2.0 Pro\t¥0.8\t¥2.0\tByteDance subsidy\nDoubao Seed 2.0 Mini\t¥0.15\t¥0.3\tUltra cheap\nMiniMax M2.5\t¥1.0\t¥3.0\tCan run locally\nStep 3.5 Flash\t¥0.7\t¥1.4\tFastest inference\n\nPrices as of Feb 2026. All providers offer free tiers or credits for new users.\n\nAll APIs are OpenAI-Compatible\n\nEvery provider listed uses the OpenAI chat/completions format. No special SDKs needed — just change baseUrl and apiKey.\n\nFeatures\nAuto-fallback: If one provider is down, automatically try the next\nCost tracking: See per-model token usage and estimated cost\nSmart routing: Describe your task, get the best model recommendation\nBatch compare: Send the same prompt to multiple models, compare outputs\nContext-aware: Remembers your model preference per conversation topic\nLinks\n🦐 Try our AI Plaza: https://ai.xudd-v.com\n📦 ClawHub: https://clawhub.ai/Xdd-xund/chinese-llm-router\n💬 Feedback: https://ai.xudd-v.com/connect.html" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Xdd-xund/chinese-llm-router", "publisherUrl": "https://clawhub.ai/Xdd-xund/chinese-llm-router", "owner": "Xdd-xund", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/chinese-llm-router", "downloadUrl": "https://openagent3.xyz/downloads/chinese-llm-router", "agentUrl": "https://openagent3.xyz/skills/chinese-llm-router/agent", "manifestUrl": "https://openagent3.xyz/skills/chinese-llm-router/agent.json", "briefUrl": "https://openagent3.xyz/skills/chinese-llm-router/agent.md" } }