diff --git a/README.md b/README.md
index 8dbfa9be..53f0b261 100644
--- a/README.md
+++ b/README.md
@@ -233,7 +233,7 @@ export STRIX_REASONING_EFFORT="high"  # control thinking effort (default: high,
 - [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) — `anthropic/claude-sonnet-4-6`
 - [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) — `vertex_ai/gemini-3-pro-preview`
 
-See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.
+See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Novita AI, Vertex AI, Bedrock, Azure, and local models.
 
 ## Enterprise
 
diff --git a/docs/llm-providers/overview.mdx b/docs/llm-providers/overview.mdx
index 2412be05..3b986ff4 100644
--- a/docs/llm-providers/overview.mdx
+++ b/docs/llm-providers/overview.mdx
@@ -32,6 +32,10 @@ export STRIX_LLM="openai/gpt-5"
 export LLM_API_KEY="your-api-key"
 ```
 
+<Note>
+  **Novita AI** requires an additional `LLM_API_BASE` variable pointing to their OpenAI-compatible endpoint. See the [Novita AI guide](/llm-providers/novita) for full setup instructions.
+</Note>
+
 ## Local Models
 
 Run models locally with [Ollama](https://ollama.com), [LM Studio](https://lmstudio.ai), or any OpenAI-compatible server: