Tencent SkillHub · Communication & Collaboration

Add SiliconFlow Provider (98+ Models, Free Tier)

为 OpenClaw 配置硅基流动 (SiliconFlow) 作为模型源。SiliconFlow 是国内领先的 AI 模型推理平台，提供 98+ 个 chat 模型，包含多个免费模型（Qwen3-8B、DeepSeek-R1-8B 等）。使用标准 OpenAI 协议（openai-completions）。包含 provider 注册、模型定义、别名配置、fallback 链接入和验证的完整流程。当管理员说想"加硅基流动"、"配 SiliconFlow"、"接入 SF 模型"、"加 Kimi"、"加 Qwen3"、"加免费模型"、"接入 DeepSeek V3.2"时使用此 skill。

skill openclawclawhub Free

0 Downloads

0 Stars

0 Installs

0 Score

High Signal

⬇ 0 downloads ★ 0 stars Unverified but indexed

Install for OpenClaw

Quick setup

Download the package from Yavira.
Extract the archive and review SKILL.md first.
Import or place the package into your OpenClaw setup.

Requirements

Target platform: OpenClaw
Install method: Manual import
Extraction: Extract archive
Prerequisites: OpenClaw
Primary doc: SKILL.md

Package facts

Download mode: Yavira redirect
Package format: ZIP package
Source platform: Tencent SkillHub
What's included: README.md, SKILL.md

Validation

Use the Yavira download entry.
Review SKILL.md after the package is downloaded.
Confirm the extracted package contains the expected setup assets.

Install with your agent

Agent handoff

Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.

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.

New install

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.

Upgrade existing

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.

Open Send to Agent page Open JSON manifest Open Markdown brief

Trust & source

Release facts

Source: Tencent SkillHub
Verification: Indexed source record
Version: 1.0.0

Provenance

Publisher: jooey
Source page: View original listing
Canonical URL: Open canonical page

Documentation

ClawHub primary doc Primary doc: SKILL.md 18 sections Open source page

配置 SiliconFlow Provider（硅基流动模型推理平台）

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。核心优势： 🆓 多个免费模型：Qwen3-8B、DeepSeek-R1-8B 等完全免费 💰 价格极低：旗舰模型价格仅为官方的 30-50% 🔌 OpenAI 兼容：标准 openai-completions 协议，即插即用 📦 模型丰富：一个 API Key 访问所有模型如果还没有 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 项目值Provider 名称siliconflowAPI 协议openai-completionsBase URLhttps://api.siliconflow.cn/v1认证方式Bearer Token (API Key)

前置条件

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）

获取 API Key

验证 API Key

curl -s 'https://api.siliconflow.cn/v1/user/info' \ -H 'Authorization: Bearer <YOUR_API_KEY>' | python3 -m json.tool 期望返回 "status": "normal" 和余额信息。

🆓 免费模型（无限使用）

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

💰 性价比模型（便宜好用）

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

🚀 旗舰模型（重要任务）

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

Step 1: 备份配置

cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.backup.$(date +%Y%m%d_%H%M%S)

Step 2: 添加 Provider

通过 gateway config.patch 添加 SiliconFlow provider。以下为推荐配置（8 个精选模型）： { "models": { "providers": { "siliconflow": { "baseUrl": "https://api.siliconflow.cn/v1", "apiKey": "<YOUR_API_KEY>", "api": "openai-completions", "models": [ { "id": "Qwen/Qwen3-8B", "name": "Qwen3 8B (Free)", "reasoning": false, "input": ["text"], "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 32768, "maxTokens": 8192 }, { "id": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", "name": "DeepSeek R1 Qwen3 8B (Free)", "reasoning": true, "input": ["text"], "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 32768, "maxTokens": 8192 }, { "id": "Qwen/Qwen3-30B-A3B", "name": "Qwen3 30B MoE", "reasoning": false, "input": ["text"], "cost": {"input": 0.7, "output": 2.8, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 32768, "maxTokens": 8192 }, { "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "name": "Qwen3 Coder 30B", "reasoning": false, "input": ["text"], "cost": {"input": 0.7, "output": 2.8, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 32768, "maxTokens": 8192 }, { "id": "deepseek-ai/DeepSeek-V3.2", "name": "DeepSeek V3.2", "reasoning": false, "input": ["text"], "cost": {"input": 2.0, "output": 3.0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 128000, "maxTokens": 8192 }, { "id": "deepseek-ai/DeepSeek-R1", "name": "DeepSeek R1", "reasoning": true, "input": ["text"], "cost": {"input": 4.0, "output": 16.0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 128000, "maxTokens": 8192 }, { "id": "Pro/moonshotai/Kimi-K2.5", "name": "Kimi K2.5", "reasoning": false, "input": ["text"], "cost": {"input": 4.0, "output": 21.0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 128000, "maxTokens": 8192 }, { "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "name": "Qwen3 Coder 480B", "reasoning": false, "input": ["text"], "cost": {"input": 8.0, "output": 16.0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 32768, "maxTokens": 8192 } ] } } } }

Step 3: 添加别名

在同一个 patch 中添加别名映射： { "agents": { "defaults": { "models": { "siliconflow/Qwen/Qwen3-8B": {"alias": "sf-qwen3-8b"}, "siliconflow/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B": {"alias": "sf-r1-8b"}, "siliconflow/Qwen/Qwen3-30B-A3B": {"alias": "sf-qwen3-30b"}, "siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct": {"alias": "sf-coder-30b"}, "siliconflow/deepseek-ai/DeepSeek-V3.2": {"alias": "sf-dsv3"}, "siliconflow/deepseek-ai/DeepSeek-R1": {"alias": "sf-r1"}, "siliconflow/Pro/moonshotai/Kimi-K2.5": {"alias": "sf-kimi"}, "siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct": {"alias": "sf-coder-480b"} } } } } ⚠️ agents.defaults.models.<id> 只允许 alias 字段！其他字段会导致 Gateway 崩溃。

Step 4: 接入 Fallback 链

将免费模型加入 fallback 链作为兜底： { "agents": { "defaults": { "model": { "fallbacks": [ "...(现有 fallbacks)...", "siliconflow/Qwen/Qwen3-8B", "siliconflow/Qwen/Qwen3-30B-A3B" ] } } } } 推荐 fallback 策略：优先放免费模型 (Qwen3-8B)，然后放便宜模型 (Qwen3-30B)。

Step 5: 验证

# 1. 配置校验 openclaw doctor # 2. 重启生效 openclaw gateway restart # 3. 确认状态 openclaw gateway status # 4. 测试模型切换 # 在聊天中输入: /model sf-kimi

查询余额

curl -s 'https://api.siliconflow.cn/v1/user/info' \ -H 'Authorization: Bearer <API_KEY>' | python3 -c " import json,sys; d=json.load(sys.stdin)['data'] print(f'充值余额: ¥{d[\"chargeBalance\"]}') print(f'赠送余额: ¥{d[\"balance\"]}') print(f'总余额: ¥{d[\"totalBalance\"]}') "

查看可用模型

# 所有 chat 模型 curl -s 'https://api.siliconflow.cn/v1/models?sub_type=chat' \ -H 'Authorization: Bearer <API_KEY>' | python3 -c " import json,sys models = json.load(sys.stdin)['data'] print(f'共 {len(models)} 个 chat 模型') for m in sorted(models, key=lambda x: x['id']): print(f' {m[\"id\"]}') "

测试模型

curl -s 'https://api.siliconflow.cn/v1/chat/completions' \ -H 'Authorization: Bearer <API_KEY>' \ -H 'Content-Type: application/json' \ -d '{ "model": "Qwen/Qwen3-8B", "messages": [{"role":"user","content":"说OK"}], "max_tokens": 5 }'

添加更多模型

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。

注意事项

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 Pro 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 cost 字段单位：¥/百万 tokens (1M tokens) 注册链接：https://cloud.siliconflow.cn/i/ihj5inat （邀请注册双方均获赠额度）

Category context

Messaging, meetings, inboxes, CRM, and teammate communication surfaces.

Source: Tencent SkillHub

Largest current source with strong distribution and engagement signals.

Package contents

Included in package

2 Docs

SKILL.md Primary doc
README.md Docs