diff --git a/packages/web/src/content/docs/providers.mdx b/packages/web/src/content/docs/providers.mdx
index e7befcf026cf..d549728d1333 100644
--- a/packages/web/src/content/docs/providers.mdx
+++ b/packages/web/src/content/docs/providers.mdx
@@ -1478,6 +1478,94 @@ SAP AI Core provides access to 40+ models from OpenAI, Anthropic, Google, Amazon
 
 ---
 
+### STACKIT
+
+STACKIT AI Model Serving provides fully managed hosting environment for AI models, focusing on large language models (LLMs) like Llama, Mistral, and Qwen, with maximum data sovereignty on European infrastructure.
+
+1. Head over to [STACKIT Portal](https://portal.stackit.cloud), navigate to **AI Model Serving**, and create an auth token for your project.
+
+   :::tip
+   You need a STACKIT customer account, user account, and project before creating auth tokens.
+   :::
+
+2. Run the `/connect` command and search for **STACKIT**.
+
+   ```txt
+   /connect
+   ```
+
+3. Enter your STACKIT AI Model Serving auth token.
+
+   ```txt
+   ┌ API key
+   │
+   │
+   └ enter
+   ```
+
+4. Run the `/models` command to select from available models like _Qwen3-VL 235B_ or _Llama 3.3 70B_.
+
+   ```txt
+   /models
+   ```
+
+#### Available Models
+
+**Text Models:**
+
+- **Qwen3-VL 235B** - Vision-language model with 218K context, multimodal input
+- **Llama 3.3 70B** - General purpose LLM with 128K context, tool calling enabled
+- **GPT-OSS 120B** - Strong reasoning model with 131K context, tool calling enabled
+- **Gemma 3 27B** - Multimodal model with 37K context, 140+ languages
+- **Mistral-Nemo** - Multilingual LLM with 128K context, optimized for commercial use
+- **Llama 3.1 8B** - Efficient model with 128K context, tool calling enabled
+
+**Embedding Models:**
+
+- **E5 Mistral 7B** - Text embedding model (4096 dimensions)
+- **Qwen3 Vision-Language Embedding** - Multimodal embedding model for text and images
+
+:::note
+All models use OpenAI-compatible API endpoints. Rate limits apply: 200,000 TPM and 30-80 RPM for chat models, 600 RPM for embedding models.
+:::
+
+#### Custom Configuration
+
+You can also configure STACKIT manually in your `opencode.json`:
+
+```json title="opencode.json" "stackit" {5, 6, 8, 10-14}
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "stackit": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "STACKIT AI Model Serving",
+      "options": {
+        "baseURL": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1"
+      },
+      "models": {
+        "qwen3-vl-235b": {
+          "name": "Qwen3-VL 235B",
+          "limit": {
+            "context": 218000,
+            "output": 65536
+          }
+        },
+        "llama-33-70b": {
+          "name": "Llama 3.3 70B",
+          "limit": {
+            "context": 128000,
+            "output": 65536
+          }
+        }
+      }
+    }
+  }
+}
+```
+
+---
+
 ### OVHcloud AI Endpoints
 
 1. Head over to the [OVHcloud panel](https://ovh.com/manager). Navigate to the `Public Cloud` section, `AI & Machine Learning` > `AI Endpoints` and in `API Keys` tab, click **Create a new API key**.