diff --git a/README.md b/README.md
index 03789de..dfe799a 100644
--- a/README.md
+++ b/README.md
@@ -583,6 +583,7 @@ Config file: `~/.nanobot/config.json`
 | `gemini` | LLM (Gemini direct) | [aistudio.google.com](https://aistudio.google.com) |
 | `minimax` | LLM (MiniMax direct) | [platform.minimax.io](https://platform.minimax.io) |
 | `aihubmix` | LLM (API gateway, access to all models) | [aihubmix.com](https://aihubmix.com) |
+| `siliconflow` | LLM (SiliconFlow/硅基流动, API gateway) | [siliconflow.cn](https://siliconflow.cn) |
 | `dashscope` | LLM (Qwen) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
 | `moonshot` | LLM (Moonshot/Kimi) | [platform.moonshot.cn](https://platform.moonshot.cn) |
 | `zhipu` | LLM (Zhipu GLM) | [open.bigmodel.cn](https://open.bigmodel.cn) |
diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.py
index d267069..49b735c 100644
--- a/nanobot/providers/registry.py
+++ b/nanobot/providers/registry.py
@@ -119,16 +119,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         model_overrides=(),
     ),
 
-    # SiliconFlow (硅基流动): OpenAI-compatible gateway hosting multiple models.
-    # strip_model_prefix=False: SiliconFlow model names include org prefix
-    # (e.g. "Qwen/Qwen2.5-14B-Instruct", "deepseek-ai/DeepSeek-V3")
-    # which is part of the model ID and must NOT be stripped.
+    # SiliconFlow (硅基流动): OpenAI-compatible gateway, model names keep org prefix
     ProviderSpec(
         name="siliconflow",
         keywords=("siliconflow",),
-        env_key="OPENAI_API_KEY",            # OpenAI-compatible
+        env_key="OPENAI_API_KEY",
         display_name="SiliconFlow",
-        litellm_prefix="openai",             # → openai/{model}
+        litellm_prefix="openai",
         skip_prefixes=(),
         env_extras=(),
         is_gateway=True,