Add SiliconFlow Provider (98+ Models, Free Tier)

Verified

Add SiliconFlow Provider (98+ Models, Free Tier) — AI and machine learning tool. Supports OpenClaw, chat, Qwen3, DeepSeek-R1.

565 downloads

$ Add to .claude/skills/

$ openclaw install

About This Skill

Content available in Chinese

# 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 | `siliconflow` | | API 协议 | `openai-completions` | | Base URL | `https://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

注册：https://cloud.siliconflow.cn/i/ihj5inat
进入控制台 → API 密钥 → 创建
复制 `sk-xxx` 格式的密钥

验证 API Key

```bash 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。

---

配置步骤

Step 1: 备份配置

```bash 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）：

```json { "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：

```json { "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：

```json { "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

```bash # 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 ```

---

实用 API

查询余额

```bash 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

```bash # 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

```bash 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）

Use Cases

Configure SiliconFlow as an AI model provider in OpenClaw with 98+ available models
Access free LLM models like Qwen3-8B and DeepSeek-R1-8B for zero-cost inference
Set up model fallback chains with SiliconFlow's free tier as a cost-saving backup
Compare and select from Qwen, DeepSeek, Kimi, GLM, and MiniMax model families
Add model aliases for quick switching between SiliconFlow models in chat

Pros & Cons

Pros

+Access to 98+ models through a single API key — massive model variety
+Multiple free models available for unlimited use at zero cost
+OpenAI-compatible API protocol — plug-and-play with existing infrastructure

Cons

-Documentation entirely in Chinese — not accessible to non-Chinese-speaking users
-Free models have QPS rate limits that may bottleneck high-throughput use cases
-SiliconFlow is a China-based service — may have latency issues for international users

FAQ

What does Add SiliconFlow Provider (98+ Models, Free Tier) do?

Add SiliconFlow Provider (98+ Models, Free Tier) — AI and machine learning tool. Supports OpenClaw, chat, Qwen3, DeepSeek-R1.

What platforms support Add SiliconFlow Provider (98+ Models, Free Tier)?

Add SiliconFlow Provider (98+ Models, Free Tier) is available on Claude Code, OpenClaw.

What are the use cases for Add SiliconFlow Provider (98+ Models, Free Tier)?

Configure SiliconFlow as an AI model provider in OpenClaw with 98+ available models. Access free LLM models like Qwen3-8B and DeepSeek-R1-8B for zero-cost inference. Set up model fallback chains with SiliconFlow's free tier as a cost-saving backup.

100+ free AI tools

Writing, PDF, image, and developer tools — all in your browser.

AI Humanizer

Make AI text undetectable

AI Detector

Free, unlimited

PDF Tools

Merge, split, compress

Next Step

Use the skill detail page to evaluate fit and install steps. For a direct browser workflow, move into a focused tool route instead of staying in broader support surfaces.

Open Free Tools Try AI Detector