{ "schemaVersion": "1.0", "item": { "slug": "add-siliconflow-provider", "name": "Add SiliconFlow Provider (98+ Models, Free Tier)", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/jooey/add-siliconflow-provider", "canonicalUrl": "https://clawhub.ai/jooey/add-siliconflow-provider", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/add-siliconflow-provider", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=add-siliconflow-provider", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.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. 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": "2026-04-23T16:43:11.935Z", "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/add-siliconflow-provider" }, "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/add-siliconflow-provider", "agentPageUrl": "https://openagent3.xyz/skills/add-siliconflow-provider/agent", "manifestUrl": "https://openagent3.xyz/skills/add-siliconflow-provider/agent.json", "briefUrl": "https://openagent3.xyz/skills/add-siliconflow-provider/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": "配置 SiliconFlow Provider（硅基流动模型推理平台）", "body": "SiliconFlow（硅基流动）是国内领先的 AI 模型推理平台，提供 98+ 个 chat 模型，涵盖 Qwen、DeepSeek、Kimi、GLM、MiniMax 等主流系列。\n\n核心优势：\n\n🆓 多个免费模型：Qwen3-8B、DeepSeek-R1-8B 等完全免费\n💰 价格极低：旗舰模型价格仅为官方的 30-50%\n🔌 OpenAI 兼容：标准 openai-completions 协议，即插即用\n📦 模型丰富：一个 API Key 访问所有模型\n\n如果还没有 SiliconFlow 账号，请通过邀请链接注册（双方均获赠额度）：\n👉 https://cloud.siliconflow.cn/i/ihj5inat\n\n项目值Provider 名称siliconflowAPI 协议openai-completionsBase URLhttps://api.siliconflow.cn/v1认证方式Bearer Token (API Key)" }, { "title": "前置条件", "body": "项目说明API Key在 控制台 创建，格式 sk-xxx余额免费模型无需余额；付费模型需充值（新用户注册送 ¥14）" }, { "title": "获取 API Key", "body": "注册：https://cloud.siliconflow.cn/i/ihj5inat\n进入控制台 → API 密钥 → 创建\n复制 sk-xxx 格式的密钥" }, { "title": "验证 API Key", "body": "curl -s 'https://api.siliconflow.cn/v1/user/info' \\\n -H 'Authorization: Bearer ' | python3 -m json.tool\n\n期望返回 \"status\": \"normal\" 和余额信息。" }, { "title": "🆓 免费模型（无限使用）", "body": "模型 ID说明推荐别名Qwen/Qwen3-8B通义千问 3 代 8B，综合能力强sf-qwen3-8bdeepseek-ai/DeepSeek-R1-0528-Qwen3-8BDeepSeek R1 推理蒸馏版sf-r1-8bTHUDM/glm-4-9b-chat智谱 GLM-4 9Bsf-glm4Qwen/Qwen2.5-7B-InstructQwen 2.5 7Bsf-qwen25-7bQwen/Qwen2.5-Coder-7B-InstructQwen 2.5 编码专用sf-qwen-coder-7b" }, { "title": "💰 性价比模型（便宜好用）", "body": "模型 ID输入/输出 (¥/M tokens)说明推荐别名Qwen/Qwen3-30B-A3B0.7 / 2.8MoE 架构，性价比极高sf-qwen3-30bQwen/Qwen3-Coder-30B-A3B-Instruct0.7 / 2.8编码专用 30Bsf-coder-30bdeepseek-ai/DeepSeek-V3.22.0 / 3.0DeepSeek 最新版sf-dsv3Pro/deepseek-ai/DeepSeek-V3.22.0 / 3.0Pro 加速版sf-dsv3-pro" }, { "title": "🚀 旗舰模型（重要任务）", "body": "模型 ID输入/输出 (¥/M tokens)说明推荐别名deepseek-ai/DeepSeek-R14.0 / 16.0推理模型sf-r1Pro/moonshotai/Kimi-K2.54.0 / 21.0月之暗面最强模型sf-kimiQwen/Qwen3-Coder-480B-A35B-Instruct8.0 / 16.0编码旗舰 480B MoEsf-coder-480b" }, { "title": "Step 1: 备份配置", "body": "cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.backup.$(date +%Y%m%d_%H%M%S)" }, { "title": "Step 2: 添加 Provider", "body": "通过 gateway config.patch 添加 SiliconFlow provider。以下为推荐配置（8 个精选模型）：\n\n{\n \"models\": {\n \"providers\": {\n \"siliconflow\": {\n \"baseUrl\": \"https://api.siliconflow.cn/v1\",\n \"apiKey\": \"\",\n \"api\": \"openai-completions\",\n \"models\": [\n {\n \"id\": \"Qwen/Qwen3-8B\",\n \"name\": \"Qwen3 8B (Free)\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0, \"output\": 0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B\",\n \"name\": \"DeepSeek R1 Qwen3 8B (Free)\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0, \"output\": 0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Qwen/Qwen3-30B-A3B\",\n \"name\": \"Qwen3 30B MoE\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0.7, \"output\": 2.8, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Qwen/Qwen3-Coder-30B-A3B-Instruct\",\n \"name\": \"Qwen3 Coder 30B\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0.7, \"output\": 2.8, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"deepseek-ai/DeepSeek-V3.2\",\n \"name\": \"DeepSeek V3.2\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 2.0, \"output\": 3.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 128000,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"deepseek-ai/DeepSeek-R1\",\n \"name\": \"DeepSeek R1\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 4.0, \"output\": 16.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 128000,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Pro/moonshotai/Kimi-K2.5\",\n \"name\": \"Kimi K2.5\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 4.0, \"output\": 21.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 128000,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Qwen/Qwen3-Coder-480B-A35B-Instruct\",\n \"name\": \"Qwen3 Coder 480B\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 8.0, \"output\": 16.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n }\n ]\n }\n }\n }\n}" }, { "title": "Step 3: 添加别名", "body": "在同一个 patch 中添加别名映射：\n\n{\n \"agents\": {\n \"defaults\": {\n \"models\": {\n \"siliconflow/Qwen/Qwen3-8B\": {\"alias\": \"sf-qwen3-8b\"},\n \"siliconflow/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B\": {\"alias\": \"sf-r1-8b\"},\n \"siliconflow/Qwen/Qwen3-30B-A3B\": {\"alias\": \"sf-qwen3-30b\"},\n \"siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct\": {\"alias\": \"sf-coder-30b\"},\n \"siliconflow/deepseek-ai/DeepSeek-V3.2\": {\"alias\": \"sf-dsv3\"},\n \"siliconflow/deepseek-ai/DeepSeek-R1\": {\"alias\": \"sf-r1\"},\n \"siliconflow/Pro/moonshotai/Kimi-K2.5\": {\"alias\": \"sf-kimi\"},\n \"siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct\": {\"alias\": \"sf-coder-480b\"}\n }\n }\n }\n}\n\n⚠️ agents.defaults.models. 只允许 alias 字段！ 其他字段会导致 Gateway 崩溃。" }, { "title": "Step 4: 接入 Fallback 链", "body": "将免费模型加入 fallback 链作为兜底：\n\n{\n \"agents\": {\n \"defaults\": {\n \"model\": {\n \"fallbacks\": [\n \"...(现有 fallbacks)...\",\n \"siliconflow/Qwen/Qwen3-8B\",\n \"siliconflow/Qwen/Qwen3-30B-A3B\"\n ]\n }\n }\n }\n}\n\n推荐 fallback 策略：优先放免费模型 (Qwen3-8B)，然后放便宜模型 (Qwen3-30B)。" }, { "title": "Step 5: 验证", "body": "# 1. 配置校验\nopenclaw doctor\n\n# 2. 重启生效\nopenclaw gateway restart\n\n# 3. 确认状态\nopenclaw gateway status\n\n# 4. 测试模型切换\n# 在聊天中输入: /model sf-kimi" }, { "title": "查询余额", "body": "curl -s 'https://api.siliconflow.cn/v1/user/info' \\\n -H 'Authorization: Bearer ' | python3 -c \"\nimport json,sys; d=json.load(sys.stdin)['data']\nprint(f'充值余额: ¥{d[\\\"chargeBalance\\\"]}')\nprint(f'赠送余额: ¥{d[\\\"balance\\\"]}')\nprint(f'总余额: ¥{d[\\\"totalBalance\\\"]}')\n\"" }, { "title": "查看可用模型", "body": "# 所有 chat 模型\ncurl -s 'https://api.siliconflow.cn/v1/models?sub_type=chat' \\\n -H 'Authorization: Bearer ' | python3 -c \"\nimport json,sys\nmodels = json.load(sys.stdin)['data']\nprint(f'共 {len(models)} 个 chat 模型')\nfor m in sorted(models, key=lambda x: x['id']):\n print(f' {m[\\\"id\\\"]}')\n\"" }, { "title": "测试模型", "body": "curl -s 'https://api.siliconflow.cn/v1/chat/completions' \\\n -H 'Authorization: Bearer ' \\\n -H 'Content-Type: application/json' \\\n -d '{\n \"model\": \"Qwen/Qwen3-8B\",\n \"messages\": [{\"role\":\"user\",\"content\":\"说OK\"}],\n \"max_tokens\": 5\n }'" }, { "title": "添加更多模型", "body": "SiliconFlow 有 98+ 个 chat 模型。如需添加更多，先用模型列表 API 查询可用模型，然后按 Step 2 的格式添加到 provider 的 models 数组中。" }, { "title": "热门模型速查", "body": "模型输入/输出 (¥/M tokens)特点zai-org/GLM-4.63.5 / 14.0智谱最新旗舰Pro/deepseek-ai/DeepSeek-R14.0 / 16.0Pro 加速推理moonshotai/Kimi-K2-Thinking4.0 / 16.0Kimi 思考模型Qwen/Qwen3-235B-A22B-Instruct-25072.5 / 10.0Qwen3 指令模型baidu/ERNIE-4.5-300B-A47B2.0 / 8.0百度文心stepfun-ai/step34.0 / 10.0阶跃星辰 Step3" }, { "title": "注意事项", "body": "免费模型有 QPS 限制：免费模型的并发数可能受限，适合 fallback 和低频任务\nPro 版本 vs 普通版本：Pro/ 前缀的模型使用专用推理集群，速度更快但价格略高\n模型 ID 区分大小写：必须严格匹配，如 Qwen/Qwen3-8B 不能写成 qwen/qwen3-8b\ncost 字段单位：¥/百万 tokens (1M tokens)\n\n注册链接：https://cloud.siliconflow.cn/i/ihj5inat （邀请注册双方均获赠额度）" } ], "body": "配置 SiliconFlow Provider（硅基流动模型推理平台）\n\nSiliconFlow（硅基流动）是国内领先的 AI 模型推理平台，提供 98+ 个 chat 模型，涵盖 Qwen、DeepSeek、Kimi、GLM、MiniMax 等主流系列。\n\n核心优势：\n\n🆓 多个免费模型：Qwen3-8B、DeepSeek-R1-8B 等完全免费\n💰 价格极低：旗舰模型价格仅为官方的 30-50%\n🔌 OpenAI 兼容：标准 openai-completions 协议，即插即用\n📦 模型丰富：一个 API Key 访问所有模型\n\n如果还没有 SiliconFlow 账号，请通过邀请链接注册（双方均获赠额度）： 👉 https://cloud.siliconflow.cn/i/ihj5inat\n\n项目\t值\nProvider 名称\tsiliconflow\nAPI 协议\topenai-completions\nBase URL\thttps://api.siliconflow.cn/v1\n认证方式\tBearer Token (API Key)\n前置条件\n项目\t说明\nAPI Key\t在 控制台 创建，格式 sk-xxx\n余额\t免费模型无需余额；付费模型需充值（新用户注册送 ¥14）\n获取 API Key\n注册：https://cloud.siliconflow.cn/i/ihj5inat\n进入控制台 → API 密钥 → 创建\n复制 sk-xxx 格式的密钥\n验证 API Key\ncurl -s 'https://api.siliconflow.cn/v1/user/info' \\\n -H 'Authorization: Bearer ' | python3 -m json.tool\n\n\n期望返回 \"status\": \"normal\" 和余额信息。\n\n推荐模型\n🆓 免费模型（无限使用）\n模型 ID\t说明\t推荐别名\nQwen/Qwen3-8B\t通义千问 3 代 8B，综合能力强\tsf-qwen3-8b\ndeepseek-ai/DeepSeek-R1-0528-Qwen3-8B\tDeepSeek R1 推理蒸馏版\tsf-r1-8b\nTHUDM/glm-4-9b-chat\t智谱 GLM-4 9B\tsf-glm4\nQwen/Qwen2.5-7B-Instruct\tQwen 2.5 7B\tsf-qwen25-7b\nQwen/Qwen2.5-Coder-7B-Instruct\tQwen 2.5 编码专用\tsf-qwen-coder-7b\n💰 性价比模型（便宜好用）\n模型 ID\t输入/输出 (¥/M tokens)\t说明\t推荐别名\nQwen/Qwen3-30B-A3B\t0.7 / 2.8\tMoE 架构，性价比极高\tsf-qwen3-30b\nQwen/Qwen3-Coder-30B-A3B-Instruct\t0.7 / 2.8\t编码专用 30B\tsf-coder-30b\ndeepseek-ai/DeepSeek-V3.2\t2.0 / 3.0\tDeepSeek 最新版\tsf-dsv3\nPro/deepseek-ai/DeepSeek-V3.2\t2.0 / 3.0\tPro 加速版\tsf-dsv3-pro\n🚀 旗舰模型（重要任务）\n模型 ID\t输入/输出 (¥/M tokens)\t说明\t推荐别名\ndeepseek-ai/DeepSeek-R1\t4.0 / 16.0\t推理模型\tsf-r1\nPro/moonshotai/Kimi-K2.5\t4.0 / 21.0\t月之暗面最强模型\tsf-kimi\nQwen/Qwen3-Coder-480B-A35B-Instruct\t8.0 / 16.0\t编码旗舰 480B MoE\tsf-coder-480b\n配置步骤\nStep 1: 备份配置\ncp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.backup.$(date +%Y%m%d_%H%M%S)\n\nStep 2: 添加 Provider\n\n通过 gateway config.patch 添加 SiliconFlow provider。以下为推荐配置（8 个精选模型）：\n\n{\n \"models\": {\n \"providers\": {\n \"siliconflow\": {\n \"baseUrl\": \"https://api.siliconflow.cn/v1\",\n \"apiKey\": \"\",\n \"api\": \"openai-completions\",\n \"models\": [\n {\n \"id\": \"Qwen/Qwen3-8B\",\n \"name\": \"Qwen3 8B (Free)\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0, \"output\": 0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B\",\n \"name\": \"DeepSeek R1 Qwen3 8B (Free)\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0, \"output\": 0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Qwen/Qwen3-30B-A3B\",\n \"name\": \"Qwen3 30B MoE\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0.7, \"output\": 2.8, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Qwen/Qwen3-Coder-30B-A3B-Instruct\",\n \"name\": \"Qwen3 Coder 30B\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 0.7, \"output\": 2.8, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"deepseek-ai/DeepSeek-V3.2\",\n \"name\": \"DeepSeek V3.2\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 2.0, \"output\": 3.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 128000,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"deepseek-ai/DeepSeek-R1\",\n \"name\": \"DeepSeek R1\",\n \"reasoning\": true,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 4.0, \"output\": 16.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 128000,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Pro/moonshotai/Kimi-K2.5\",\n \"name\": \"Kimi K2.5\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 4.0, \"output\": 21.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 128000,\n \"maxTokens\": 8192\n },\n {\n \"id\": \"Qwen/Qwen3-Coder-480B-A35B-Instruct\",\n \"name\": \"Qwen3 Coder 480B\",\n \"reasoning\": false,\n \"input\": [\"text\"],\n \"cost\": {\"input\": 8.0, \"output\": 16.0, \"cacheRead\": 0, \"cacheWrite\": 0},\n \"contextWindow\": 32768,\n \"maxTokens\": 8192\n }\n ]\n }\n }\n }\n}\n\nStep 3: 添加别名\n\n在同一个 patch 中添加别名映射：\n\n{\n \"agents\": {\n \"defaults\": {\n \"models\": {\n \"siliconflow/Qwen/Qwen3-8B\": {\"alias\": \"sf-qwen3-8b\"},\n \"siliconflow/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B\": {\"alias\": \"sf-r1-8b\"},\n \"siliconflow/Qwen/Qwen3-30B-A3B\": {\"alias\": \"sf-qwen3-30b\"},\n \"siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct\": {\"alias\": \"sf-coder-30b\"},\n \"siliconflow/deepseek-ai/DeepSeek-V3.2\": {\"alias\": \"sf-dsv3\"},\n \"siliconflow/deepseek-ai/DeepSeek-R1\": {\"alias\": \"sf-r1\"},\n \"siliconflow/Pro/moonshotai/Kimi-K2.5\": {\"alias\": \"sf-kimi\"},\n \"siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct\": {\"alias\": \"sf-coder-480b\"}\n }\n }\n }\n}\n\n\n⚠️ agents.defaults.models. 只允许 alias 字段！ 其他字段会导致 Gateway 崩溃。\n\nStep 4: 接入 Fallback 链\n\n将免费模型加入 fallback 链作为兜底：\n\n{\n \"agents\": {\n \"defaults\": {\n \"model\": {\n \"fallbacks\": [\n \"...(现有 fallbacks)...\",\n \"siliconflow/Qwen/Qwen3-8B\",\n \"siliconflow/Qwen/Qwen3-30B-A3B\"\n ]\n }\n }\n }\n}\n\n\n推荐 fallback 策略：优先放免费模型 (Qwen3-8B)，然后放便宜模型 (Qwen3-30B)。\n\nStep 5: 验证\n# 1. 配置校验\nopenclaw doctor\n\n# 2. 重启生效\nopenclaw gateway restart\n\n# 3. 确认状态\nopenclaw gateway status\n\n# 4. 测试模型切换\n# 在聊天中输入: /model sf-kimi\n\n实用 API\n查询余额\ncurl -s 'https://api.siliconflow.cn/v1/user/info' \\\n -H 'Authorization: Bearer ' | python3 -c \"\nimport json,sys; d=json.load(sys.stdin)['data']\nprint(f'充值余额: ¥{d[\\\"chargeBalance\\\"]}')\nprint(f'赠送余额: ¥{d[\\\"balance\\\"]}')\nprint(f'总余额: ¥{d[\\\"totalBalance\\\"]}')\n\"\n\n查看可用模型\n# 所有 chat 模型\ncurl -s 'https://api.siliconflow.cn/v1/models?sub_type=chat' \\\n -H 'Authorization: Bearer ' | python3 -c \"\nimport json,sys\nmodels = json.load(sys.stdin)['data']\nprint(f'共 {len(models)} 个 chat 模型')\nfor m in sorted(models, key=lambda x: x['id']):\n print(f' {m[\\\"id\\\"]}')\n\"\n\n测试模型\ncurl -s 'https://api.siliconflow.cn/v1/chat/completions' \\\n -H 'Authorization: Bearer ' \\\n -H 'Content-Type: application/json' \\\n -d '{\n \"model\": \"Qwen/Qwen3-8B\",\n \"messages\": [{\"role\":\"user\",\"content\":\"说OK\"}],\n \"max_tokens\": 5\n }'\n\n添加更多模型\n\nSiliconFlow 有 98+ 个 chat 模型。如需添加更多，先用模型列表 API 查询可用模型，然后按 Step 2 的格式添加到 provider 的 models 数组中。\n\n热门模型速查\n模型\t输入/输出 (¥/M tokens)\t特点\nzai-org/GLM-4.6\t3.5 / 14.0\t智谱最新旗舰\nPro/deepseek-ai/DeepSeek-R1\t4.0 / 16.0\tPro 加速推理\nmoonshotai/Kimi-K2-Thinking\t4.0 / 16.0\tKimi 思考模型\nQwen/Qwen3-235B-A22B-Instruct-2507\t2.5 / 10.0\tQwen3 指令模型\nbaidu/ERNIE-4.5-300B-A47B\t2.0 / 8.0\t百度文心\nstepfun-ai/step3\t4.0 / 10.0\t阶跃星辰 Step3\n注意事项\n免费模型有 QPS 限制：免费模型的并发数可能受限，适合 fallback 和低频任务\nPro 版本 vs 普通版本：Pro/ 前缀的模型使用专用推理集群，速度更快但价格略高\n模型 ID 区分大小写：必须严格匹配，如 Qwen/Qwen3-8B 不能写成 qwen/qwen3-8b\ncost 字段单位：¥/百万 tokens (1M tokens)\n\n注册链接：https://cloud.siliconflow.cn/i/ihj5inat （邀请注册双方均获赠额度）" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/jooey/add-siliconflow-provider", "publisherUrl": "https://clawhub.ai/jooey/add-siliconflow-provider", "owner": "jooey", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/add-siliconflow-provider", "downloadUrl": "https://openagent3.xyz/downloads/add-siliconflow-provider", "agentUrl": "https://openagent3.xyz/skills/add-siliconflow-provider/agent", "manifestUrl": "https://openagent3.xyz/skills/add-siliconflow-provider/agent.json", "briefUrl": "https://openagent3.xyz/skills/add-siliconflow-provider/agent.md" } }