{ "schemaVersion": "1.0", "item": { "slug": "openclaw-aisa-leading-chinese-llm", "name": "Chines LLM Models (MiniMax 2.5,Kimi 2.5, Qwen, Doubao, DeepSeek) with one key", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/AIsaDocs/openclaw-aisa-leading-chinese-llm", "canonicalUrl": "https://clawhub.ai/AIsaDocs/openclaw-aisa-leading-chinese-llm", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/openclaw-aisa-leading-chinese-llm", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-aisa-leading-chinese-llm", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "pricing.md", "guide-zh-CN.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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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-aisa-leading-chinese-llm" }, "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-aisa-leading-chinese-llm", "agentPageUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm/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": "AIsa Provider for OpenClaw", "body": "AIsa is a unified API gateway providing production access to China's leading AI models through official partnerships with all major Chinese AI platforms. It is an Alibaba Cloud Qwen Key Account partner, offering the full Qwen model family at discounted pricing, plus models on the Alibaba Bailian aggregation platform (DeepSeek, Kimi, GLM).\n\nAIsa also provides access to Kimi K2.5 (Moonshot AI's flagship reasoning model) at approximately 80% of official pricing.\n\n⚠️ All pricing listed below is for reference. Real-time pricing is subject to change — always check https://marketplace.aisa.one/pricing for the latest rates." }, { "title": "Option 1: Environment Variable (fastest)", "body": "export AISA_API_KEY=\"your-key-here\"\n\nOpenClaw auto-detects AISA_API_KEY and registers AIsa as a provider. No config file changes needed." }, { "title": "Option 2: Interactive Onboarding", "body": "openclaw onboard --auth-choice aisa-api-key" }, { "title": "Option 3: CLI with Key", "body": "openclaw onboard --auth-choice aisa-api-key --aisa-api-key \"your-key-here\"" }, { "title": "Option 4: Manual Config in ~/.openclaw/openclaw.json", "body": "{\n \"models\": {\n \"providers\": {\n \"aisa\": {\n \"baseUrl\": \"https://api.aisa.one/v1\",\n \"apiKey\": \"${AISA_API_KEY}\",\n \"api\": \"openai-completions\",\n \"models\": [\n {\n \"id\": \"aisa/qwen3-max\",\n \"name\": \"Qwen3 Max\",\n \"reasoning\": true,\n \"input\": [\"text\", \"image\"],\n \"contextWindow\": 256000,\n \"maxTokens\": 16384,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 1.20,\n \"output\": 4.80,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/qwen-plus-2025-12-01\",\n \"name\": \"Qwen Plus\",\n \"reasoning\": true,\n \"input\": [\"text\", \"image\"],\n \"contextWindow\": 256000,\n \"maxTokens\": 16384,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.30,\n \"output\": 0.90,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/qwen-mt-flash\",\n \"name\": \"Qwen MT Flash\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"contextWindow\": 256000,\n \"maxTokens\": 8192,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.05,\n \"output\": 0.30,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/deepseek-v3.1\",\n \"name\": \"DeepSeek V3.1\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"contextWindow\": 131072,\n \"maxTokens\": 8192,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.27,\n \"output\": 1.10,\n \"cacheRead\": 0.07,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/kimi-k2.5\",\n \"name\": \"Kimi K2.5\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"contextWindow\": 131072,\n \"maxTokens\": 8192,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.60,\n \"output\": 2.40,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n }\n ]\n }\n }\n },\n \"agents\": {\n \"defaults\": {\n \"model\": {\n \"primary\": \"aisa/qwen3-max\"\n }\n }\n }\n}" }, { "title": "Default Models (pre-configured, API-verified ✅)", "body": "ModelModel IDBest ForContextReasoningVerifiedQwen3 Maxaisa/qwen3-maxComplex reasoning, flagship tasks256K✅✅Qwen Plusaisa/qwen-plus-2025-12-01Main production model256K✅✅Qwen MT Flashaisa/qwen-mt-flashHigh-frequency, lightweight tasks256K✅✅DeepSeek V3.1aisa/deepseek-v3.1Cost-effective reasoning128K✅✅Kimi K2.5aisa/kimi-k2.5Moonshot's flagship reasoning model128K✅✅" }, { "title": "⭐ Kimi K2.5 — Moonshot AI's Flagship Model", "body": "Kimi K2.5 is Moonshot AI's latest reasoning model, accessible via AIsa at approximately 80% of official Moonshot pricing.\n\nKey features:\n\nStrong reasoning and multi-step problem solving\nCompetitive performance on coding and math benchmarks\nAvailable through AIsa's Moonshot partnership\n\n🔒 Zero Data Retention (ZDR) — Enterprise-Grade Privacy\n\nAccessing Kimi K2.5 through AIsa comes with enterprise-level Zero Data Retention guarantees. Users do not need to worry about data privacy — AIsa has executed a formal ZDR agreement with Moonshot AI.\n\nUnder the Supplemental Enterprise Service Agreement (dated 10 February 2026) between AIsa and Kimi (Moonshot AI PTE. LTD.):\n\nCustomer data is NOT retained by Moonshot after processing\nGenerated outputs are NOT stored on Moonshot's infrastructure\nNo data is used for model training — your prompts and completions remain private\nProcessing is governed by contractual enterprise terms, not consumer ToS\n\nThis makes AIsa the recommended path for privacy-sensitive or enterprise workloads that require access to Kimi K2.5. When calling Kimi K2.5 directly via Moonshot's consumer API, standard consumer data policies apply — by routing through AIsa, your data benefits from the negotiated ZDR protections.\n\n⚠️ Important: Temperature restriction\n\nKimi K2.5 only accepts temperature=1.0. Using any other value will return an error:\n\nError: invalid temperature: only 1 is allowed for this model\n\nIf your OpenClaw config or agent sets a different temperature, override it for Kimi:\n\n/model aisa/kimi-k2.5\n\nOpenClaw will use the model's default temperature when not explicitly set.\n\nKimi K2.5 Pricing Comparison (per 1M tokens):\n\nMetricAIsaMoonshot OfficialSavingsInput/1M~$0.60~$0.75~20% offOutput/1M~$2.40~$3.00~20% off\n\nActual pricing may vary. Check https://marketplace.aisa.one/pricing for real-time rates." }, { "title": "Additional Models Available via AIsa", "body": "Users can add any model supported by AIsa to their config. The full catalog includes 49+ models:\n\nQwen family (8 models):\n\nqwen3-max, qwen3-max-2026-01-23, qwen-plus-2025-12-01\nqwen-mt-flash, qwen-mt-lite\nqwen-vl-max, qwen3-vl-flash, qwen3-vl-plus (vision models)\n\nDeepSeek (4 models):\n\ndeepseek-v3.1, deepseek-v3, deepseek-v3-0324, deepseek-r1\n\nKimi / Moonshot (2 models):\n\nkimi-k2.5, kimi-k2-thinking\n\nAlso available: Claude series (10), GPT series (9), Gemini series (5), Grok series (2), and more.\n\nList all available models:\n\ncurl https://api.aisa.one/v1/models -H \"Authorization: Bearer $AISA_API_KEY\"" }, { "title": "Model ID Versioning", "body": "AIsa uses versioned model IDs for some models. If you encounter a 503 - No available channels error, the model ID may need updating.\n\nKnown model ID mappings:\n\nCommon NameCorrect AIsa Model ID❌ Does NOT workQwen Plusqwen-plus-2025-12-01qwen3-plus, qwen-plus, qwen-plus-latestQwen Flashqwen-mt-flashqwen3-flash, qwen-turbo, qwen-turbo-latestQwen Maxqwen3-max(works as-is)DeepSeek V3.1deepseek-v3.1(works as-is)Kimi K2.5kimi-k2.5(works as-is)\n\nTo check the latest available model IDs:\n\ncurl https://api.aisa.one/v1/models -H \"Authorization: Bearer $AISA_API_KEY\"" }, { "title": "Switching Models", "body": "In chat (TUI):\n\n/model aisa/qwen3-max\n/model aisa/deepseek-v3.1\n/model aisa/kimi-k2.5\n\nVia CLI:\n\nopenclaw models set aisa/qwen3-max" }, { "title": "Pricing Comparison (per 1M tokens)", "body": "All pricing below is for reference. Real-time pricing is subject to change — always check https://marketplace.aisa.one/pricing for the latest rates." }, { "title": "Qwen MT Flash (lightweight)", "body": "AIsa: $0.05 input / $0.30 output (~50% off retail)\nBailian Official: $0.10 / $0.40\nOpenRouter: $0.11-0.13 / $0.45-0.50" }, { "title": "Qwen Plus (production)", "body": "AIsa: $0.30 input / $0.90 output (~25% off retail)\nBailian Official: $0.40 / $1.20\nOpenRouter: $0.45-0.50 / $1.35-1.50" }, { "title": "Qwen3 Max (flagship)", "body": "AIsa: $1.20 input / $4.80 output (~40% off retail)\nBailian Official: $2.00 / $8.00\nOpenRouter: $2.20-2.50 / $9.00-10.00" }, { "title": "Kimi K2.5 (Moonshot flagship)", "body": "AIsa: ~$0.60 input / ~$2.40 output (~20% off official Moonshot pricing)\nMoonshot Official: ~$0.75 / ~$3.00\nOpenRouter: Limited availability" }, { "title": "Cost at scale: 500M tokens/month on Qwen-Max", "body": "OpenRouter: ~$4,000-4,250/month\nBailian Official: ~$3,400/month\nAIsa: ~$2,040/month (saves $16,320-26,520/year)" }, { "title": "Official Partnerships", "body": "AIsa maintains verified partnerships with:\n\nAlibaba Cloud — Qwen Key Account (full model family, 3 global regions: CN, US-Virginia, Singapore)\nBytePlus — Doubao by ByteDance\nDeepSeek — via Alibaba Cloud integration\nMoonshot — Kimi K2.5 integration, with enterprise Zero Data Retention (ZDR) agreement (effective Feb 10, 2026)" }, { "title": "Qwen Region Support", "body": "AIsa provides access to Qwen models across 3 global regions via Alibaba Cloud:\n\n🇨🇳 China (default)\n🇺🇸 US (Virginia)\n🇸🇬 Singapore\n\nThis is unique to AIsa's Key Account status. Other providers like OpenRouter or the free Qwen Portal typically route through CN only." }, { "title": "Response Latency (tested Feb 2026)", "body": "ModelAvg LatencyRatingQwen3 Max~1,577 ms⭐⭐⭐⭐⭐ FastestQwen MT Flash~1,918 ms⭐⭐⭐⭐ FastKimi K2.5~2,647 ms⭐⭐⭐ MediumDeepSeek V3.1~3,002 ms⭐⭐⭐ MediumQwen Plus~8,207 ms⭐⭐ Slower" }, { "title": "\"503 - No available channels\" error", "body": "The model ID may be incorrect or outdated. Check the Model ID Versioning section above for correct IDs. Common fixes:\n\nqwen3-plus → use qwen-plus-2025-12-01\nqwen3-flash → use qwen-mt-flash" }, { "title": "\"Model not found\" error", "body": "Ensure the model ID uses the aisa/ prefix in OpenClaw config:\n\n✅ aisa/qwen3-max\n❌ qwen3-max" }, { "title": "Kimi K2.5 \"invalid temperature\" error", "body": "Kimi K2.5 only accepts temperature=1.0. If your config sets a different temperature, add a model-specific override or let OpenClaw use the default." }, { "title": "Kimi K2.5 empty response", "body": "In rare cases Kimi K2.5 may return empty content while consuming output tokens. Retry the request — this is typically transient." }, { "title": "API key not detected", "body": "Check env var: echo $AISA_API_KEY\nOr verify in config: openclaw config get auth.profiles\nRe-run onboarding: openclaw onboard --auth-choice aisa-api-key" }, { "title": "Streaming not working", "body": "AIsa uses the OpenAI-compatible API (openai-completions). Ensure your config has:\n\n\"api\": \"openai-completions\"" }, { "title": "Rate limits or daily caps", "body": "AIsa has no daily request limits (unlike the free Qwen Portal which caps at 2,000 req/day)." }, { "title": "Get an API Key", "body": "Visit https://marketplace.aisa.one/\nSign up and create an API key\nSet it as AISA_API_KEY or use the onboarding wizard" }, { "title": "Notes", "body": "AIsa's endpoint is OpenAI-compatible (https://api.aisa.one/v1)\nAll models support streaming and function calling\nsupportsDeveloperRole is set to false for Qwen models\nDefault context window: 256,000 tokens (Qwen) or 131,072 tokens (DeepSeek/Kimi)\nReasoning (thinking) is enabled for all default models\nKimi K2.5 requires temperature=1.0 — other values cause API errors\nKimi K2.5 via AIsa is covered by enterprise Zero Data Retention (ZDR) — data is not retained or used for training\nImage/Video generation models (WAN) are available but require separate configuration\nAIsa API supports 49+ models total — use the models endpoint to discover all available options" } ], "body": "AIsa Provider for OpenClaw\n\nAIsa is a unified API gateway providing production access to China's leading AI models through official partnerships with all major Chinese AI platforms. It is an Alibaba Cloud Qwen Key Account partner, offering the full Qwen model family at discounted pricing, plus models on the Alibaba Bailian aggregation platform (DeepSeek, Kimi, GLM).\n\nAIsa also provides access to Kimi K2.5 (Moonshot AI's flagship reasoning model) at approximately 80% of official pricing.\n\n⚠️ All pricing listed below is for reference. Real-time pricing is subject to change — always check https://marketplace.aisa.one/pricing for the latest rates.\n\nQuick Setup\nOption 1: Environment Variable (fastest)\nexport AISA_API_KEY=\"your-key-here\"\n\n\nOpenClaw auto-detects AISA_API_KEY and registers AIsa as a provider. No config file changes needed.\n\nOption 2: Interactive Onboarding\nopenclaw onboard --auth-choice aisa-api-key\n\nOption 3: CLI with Key\nopenclaw onboard --auth-choice aisa-api-key --aisa-api-key \"your-key-here\"\n\nOption 4: Manual Config in ~/.openclaw/openclaw.json\n{\n \"models\": {\n \"providers\": {\n \"aisa\": {\n \"baseUrl\": \"https://api.aisa.one/v1\",\n \"apiKey\": \"${AISA_API_KEY}\",\n \"api\": \"openai-completions\",\n \"models\": [\n {\n \"id\": \"aisa/qwen3-max\",\n \"name\": \"Qwen3 Max\",\n \"reasoning\": true,\n \"input\": [\"text\", \"image\"],\n \"contextWindow\": 256000,\n \"maxTokens\": 16384,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 1.20,\n \"output\": 4.80,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/qwen-plus-2025-12-01\",\n \"name\": \"Qwen Plus\",\n \"reasoning\": true,\n \"input\": [\"text\", \"image\"],\n \"contextWindow\": 256000,\n \"maxTokens\": 16384,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.30,\n \"output\": 0.90,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/qwen-mt-flash\",\n \"name\": \"Qwen MT Flash\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"contextWindow\": 256000,\n \"maxTokens\": 8192,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.05,\n \"output\": 0.30,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/deepseek-v3.1\",\n \"name\": \"DeepSeek V3.1\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"contextWindow\": 131072,\n \"maxTokens\": 8192,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.27,\n \"output\": 1.10,\n \"cacheRead\": 0.07,\n \"cacheWrite\": 0\n }\n },\n {\n \"id\": \"aisa/kimi-k2.5\",\n \"name\": \"Kimi K2.5\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"contextWindow\": 131072,\n \"maxTokens\": 8192,\n \"supportsDeveloperRole\": false,\n \"cost\": {\n \"input\": 0.60,\n \"output\": 2.40,\n \"cacheRead\": 0,\n \"cacheWrite\": 0\n }\n }\n ]\n }\n }\n },\n \"agents\": {\n \"defaults\": {\n \"model\": {\n \"primary\": \"aisa/qwen3-max\"\n }\n }\n }\n}\n\nAvailable Models\nDefault Models (pre-configured, API-verified ✅)\nModel\tModel ID\tBest For\tContext\tReasoning\tVerified\nQwen3 Max\taisa/qwen3-max\tComplex reasoning, flagship tasks\t256K\t✅\t✅\nQwen Plus\taisa/qwen-plus-2025-12-01\tMain production model\t256K\t✅\t✅\nQwen MT Flash\taisa/qwen-mt-flash\tHigh-frequency, lightweight tasks\t256K\t✅\t✅\nDeepSeek V3.1\taisa/deepseek-v3.1\tCost-effective reasoning\t128K\t✅\t✅\nKimi K2.5\taisa/kimi-k2.5\tMoonshot's flagship reasoning model\t128K\t✅\t✅\n⭐ Kimi K2.5 — Moonshot AI's Flagship Model\n\nKimi K2.5 is Moonshot AI's latest reasoning model, accessible via AIsa at approximately 80% of official Moonshot pricing.\n\nKey features:\n\nStrong reasoning and multi-step problem solving\nCompetitive performance on coding and math benchmarks\nAvailable through AIsa's Moonshot partnership\n🔒 Zero Data Retention (ZDR) — Enterprise-Grade Privacy\n\nAccessing Kimi K2.5 through AIsa comes with enterprise-level Zero Data Retention guarantees. Users do not need to worry about data privacy — AIsa has executed a formal ZDR agreement with Moonshot AI.\n\nUnder the Supplemental Enterprise Service Agreement (dated 10 February 2026) between AIsa and Kimi (Moonshot AI PTE. LTD.):\n\nCustomer data is NOT retained by Moonshot after processing\nGenerated outputs are NOT stored on Moonshot's infrastructure\nNo data is used for model training — your prompts and completions remain private\nProcessing is governed by contractual enterprise terms, not consumer ToS\n\nThis makes AIsa the recommended path for privacy-sensitive or enterprise workloads that require access to Kimi K2.5. When calling Kimi K2.5 directly via Moonshot's consumer API, standard consumer data policies apply — by routing through AIsa, your data benefits from the negotiated ZDR protections.\n\n⚠️ Important: Temperature restriction\n\nKimi K2.5 only accepts temperature=1.0. Using any other value will return an error:\n\nError: invalid temperature: only 1 is allowed for this model\n\n\nIf your OpenClaw config or agent sets a different temperature, override it for Kimi:\n\n/model aisa/kimi-k2.5\n\n\nOpenClaw will use the model's default temperature when not explicitly set.\n\nKimi K2.5 Pricing Comparison (per 1M tokens):\n\nMetric\tAIsa\tMoonshot Official\tSavings\nInput/1M\t~$0.60\t~$0.75\t~20% off\nOutput/1M\t~$2.40\t~$3.00\t~20% off\n\nActual pricing may vary. Check https://marketplace.aisa.one/pricing for real-time rates.\n\nAdditional Models Available via AIsa\n\nUsers can add any model supported by AIsa to their config. The full catalog includes 49+ models:\n\nQwen family (8 models):\n\nqwen3-max, qwen3-max-2026-01-23, qwen-plus-2025-12-01\nqwen-mt-flash, qwen-mt-lite\nqwen-vl-max, qwen3-vl-flash, qwen3-vl-plus (vision models)\n\nDeepSeek (4 models):\n\ndeepseek-v3.1, deepseek-v3, deepseek-v3-0324, deepseek-r1\n\nKimi / Moonshot (2 models):\n\nkimi-k2.5, kimi-k2-thinking\n\nAlso available: Claude series (10), GPT series (9), Gemini series (5), Grok series (2), and more.\n\nList all available models:\n\ncurl https://api.aisa.one/v1/models -H \"Authorization: Bearer $AISA_API_KEY\"\n\nModel ID Versioning\n\nAIsa uses versioned model IDs for some models. If you encounter a 503 - No available channels error, the model ID may need updating.\n\nKnown model ID mappings:\n\nCommon Name\tCorrect AIsa Model ID\t❌ Does NOT work\nQwen Plus\tqwen-plus-2025-12-01\tqwen3-plus, qwen-plus, qwen-plus-latest\nQwen Flash\tqwen-mt-flash\tqwen3-flash, qwen-turbo, qwen-turbo-latest\nQwen Max\tqwen3-max\t(works as-is)\nDeepSeek V3.1\tdeepseek-v3.1\t(works as-is)\nKimi K2.5\tkimi-k2.5\t(works as-is)\n\nTo check the latest available model IDs:\n\ncurl https://api.aisa.one/v1/models -H \"Authorization: Bearer $AISA_API_KEY\"\n\nSwitching Models\n\nIn chat (TUI):\n\n/model aisa/qwen3-max\n/model aisa/deepseek-v3.1\n/model aisa/kimi-k2.5\n\n\nVia CLI:\n\nopenclaw models set aisa/qwen3-max\n\nPricing Comparison (per 1M tokens)\n\nAll pricing below is for reference. Real-time pricing is subject to change — always check https://marketplace.aisa.one/pricing for the latest rates.\n\nQwen MT Flash (lightweight)\nAIsa: $0.05 input / $0.30 output (~50% off retail)\nBailian Official: $0.10 / $0.40\nOpenRouter: $0.11-0.13 / $0.45-0.50\nQwen Plus (production)\nAIsa: $0.30 input / $0.90 output (~25% off retail)\nBailian Official: $0.40 / $1.20\nOpenRouter: $0.45-0.50 / $1.35-1.50\nQwen3 Max (flagship)\nAIsa: $1.20 input / $4.80 output (~40% off retail)\nBailian Official: $2.00 / $8.00\nOpenRouter: $2.20-2.50 / $9.00-10.00\nKimi K2.5 (Moonshot flagship)\nAIsa: ~$0.60 input / ~$2.40 output (~20% off official Moonshot pricing)\nMoonshot Official: ~$0.75 / ~$3.00\nOpenRouter: Limited availability\nCost at scale: 500M tokens/month on Qwen-Max\nOpenRouter: ~$4,000-4,250/month\nBailian Official: ~$3,400/month\nAIsa: ~$2,040/month (saves $16,320-26,520/year)\nOfficial Partnerships\n\nAIsa maintains verified partnerships with:\n\nAlibaba Cloud — Qwen Key Account (full model family, 3 global regions: CN, US-Virginia, Singapore)\nBytePlus — Doubao by ByteDance\nDeepSeek — via Alibaba Cloud integration\nMoonshot — Kimi K2.5 integration, with enterprise Zero Data Retention (ZDR) agreement (effective Feb 10, 2026)\nQwen Region Support\n\nAIsa provides access to Qwen models across 3 global regions via Alibaba Cloud:\n\n🇨🇳 China (default)\n🇺🇸 US (Virginia)\n🇸🇬 Singapore\n\nThis is unique to AIsa's Key Account status. Other providers like OpenRouter or the free Qwen Portal typically route through CN only.\n\nResponse Latency (tested Feb 2026)\nModel\tAvg Latency\tRating\nQwen3 Max\t~1,577 ms\t⭐⭐⭐⭐⭐ Fastest\nQwen MT Flash\t~1,918 ms\t⭐⭐⭐⭐ Fast\nKimi K2.5\t~2,647 ms\t⭐⭐⭐ Medium\nDeepSeek V3.1\t~3,002 ms\t⭐⭐⭐ Medium\nQwen Plus\t~8,207 ms\t⭐⭐ Slower\nTroubleshooting\n\"503 - No available channels\" error\n\nThe model ID may be incorrect or outdated. Check the Model ID Versioning section above for correct IDs. Common fixes:\n\nqwen3-plus → use qwen-plus-2025-12-01\nqwen3-flash → use qwen-mt-flash\n\"Model not found\" error\n\nEnsure the model ID uses the aisa/ prefix in OpenClaw config:\n\n✅ aisa/qwen3-max\n❌ qwen3-max\n\nKimi K2.5 \"invalid temperature\" error\n\nKimi K2.5 only accepts temperature=1.0. If your config sets a different temperature, add a model-specific override or let OpenClaw use the default.\n\nKimi K2.5 empty response\n\nIn rare cases Kimi K2.5 may return empty content while consuming output tokens. Retry the request — this is typically transient.\n\nAPI key not detected\nCheck env var: echo $AISA_API_KEY\nOr verify in config: openclaw config get auth.profiles\nRe-run onboarding: openclaw onboard --auth-choice aisa-api-key\nStreaming not working\n\nAIsa uses the OpenAI-compatible API (openai-completions). Ensure your config has:\n\n\"api\": \"openai-completions\"\n\nRate limits or daily caps\n\nAIsa has no daily request limits (unlike the free Qwen Portal which caps at 2,000 req/day).\n\nGet an API Key\nVisit https://marketplace.aisa.one/\nSign up and create an API key\nSet it as AISA_API_KEY or use the onboarding wizard\nNotes\nAIsa's endpoint is OpenAI-compatible (https://api.aisa.one/v1)\nAll models support streaming and function calling\nsupportsDeveloperRole is set to false for Qwen models\nDefault context window: 256,000 tokens (Qwen) or 131,072 tokens (DeepSeek/Kimi)\nReasoning (thinking) is enabled for all default models\nKimi K2.5 requires temperature=1.0 — other values cause API errors\nKimi K2.5 via AIsa is covered by enterprise Zero Data Retention (ZDR) — data is not retained or used for training\nImage/Video generation models (WAN) are available but require separate configuration\nAIsa API supports 49+ models total — use the models endpoint to discover all available options" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/AIsaDocs/openclaw-aisa-leading-chinese-llm", "publisherUrl": "https://clawhub.ai/AIsaDocs/openclaw-aisa-leading-chinese-llm", "owner": "AIsaDocs", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm", "downloadUrl": "https://openagent3.xyz/downloads/openclaw-aisa-leading-chinese-llm", "agentUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-aisa-leading-chinese-llm/agent.md" } }