diff --git a/docs/configurations/using-custom-llm.mdx b/docs/configurations/using-custom-llm.mdx
new file mode 100644
index 00000000..e4db8d8f
--- /dev/null
+++ b/docs/configurations/using-custom-llm.mdx
@@ -0,0 +1,30 @@
+---
+title: 'Using OpenAI-Compatible APIs'
+description: 'Presenton supports OpenAI-compatible APIs, allowing you to connect to any custom LLM backend that follows the OpenAI API format.'
+---
+
+### 🌐 Example: Run Presenton with a Custom LLM
+
+```bash
+docker run -it --name presenton -p 5000:80 \
+  -e LLM="custom" \
+  -e CUSTOM_LLM_URL="http://XXXXXXXXXXX/v1" \
+  -e CUSTOM_LLM_API_KEY="your_custom_api_key" \
+  -e CUSTOM_MODEL="your-model-name" \
+  -e CAN_CHANGE_KEYS="false" \
+  -v "./user_data:/app/user_data" \
+  ghcr.io/presenton/presenton:latest
+```
+
+---
+
+### 🔧 Environment Variables for Custom LLM
+
+| Variable             | Description                                                             |
+| -------------------- | ----------------------------------------------------------------------- |
+| `LLM="custom"`       | Use the `custom` value to enable OpenAI-compatible API support          |
+| `CUSTOM_LLM_URL`     | Base URL of your OpenAI-compatible API (e.g. `http://XXXXXXXXXXX/v1`)   |
+| `CUSTOM_LLM_API_KEY` | API key used for authorization (`Bearer` header)                        |
+| `CUSTOM_MODEL`       | ID of the model to use (as defined by your API provider)                |
+| `PEXELS_API_KEY`     | *(Optional)* Used to fetch high-quality images to enhance presentations |
+| `CAN_CHANGE_KEYS`    | Set to `false` to hide API keys from the frontend                       |
\ No newline at end of file
diff --git a/docs/configurations/using-gpu.mdx b/docs/configurations/using-gpu.mdx
index 6c3c106a..8af32213 100644
--- a/docs/configurations/using-gpu.mdx
+++ b/docs/configurations/using-gpu.mdx
@@ -33,5 +33,5 @@ docker run -it --name presenton --gpus=all -p 5000:80 \
   -e PEXELS_API_KEY="your_pexels_api_key" \
   -e CAN_CHANGE_KEYS="false" \
   -v "./user_data:/app/user_data" \
-  ghcr.io/presenton/presenton:v0.3.0-beta
+  ghcr.io/presenton/presenton:latest
 ```
\ No newline at end of file
diff --git a/docs/configurations/using-ollama-models.mdx b/docs/configurations/using-ollama-models.mdx
index 4db93e95..ca84bcc6 100644
--- a/docs/configurations/using-ollama-models.mdx
+++ b/docs/configurations/using-ollama-models.mdx
@@ -16,7 +16,7 @@ docker run -it --name presenton -p 5000:80 \
   -e PEXELS_API_KEY="your_pexels_api_key" \
   -e CAN_CHANGE_KEYS="false" \
   -v "./user_data:/app/user_data" \
-  ghcr.io/presenton/presenton:v0.3.0-beta
+  ghcr.io/presenton/presenton:latest
 ```
 
 ### 🚀 Example: Run Presenton with you own Ollama server
@@ -29,7 +29,7 @@ docker run -it --name presenton -p 5000:80 \
   -e PEXELS_API_KEY="your_pexels_api_key" \
   -e CAN_CHANGE_KEYS="false" \
   -v "./user_data:/app/user_data" \
-  ghcr.io/presenton/presenton:v0.3.0-beta
+  ghcr.io/presenton/presenton:latest
 ```
 
 
diff --git a/docs/development.mdx b/docs/development.mdx
index 65fd3dce..ca7f7e9e 100644
--- a/docs/development.mdx
+++ b/docs/development.mdx
@@ -19,9 +19,15 @@ cd presenton
 
 Build and start the development environment using Docker Compose:
 
+- Without GPU
+
 ```bash
 docker compose up development --build
 ```
+- With GPU
+```bash
+docker compose up development-gpu --build
+```
 
 This command will build the development container and start the app. Once running, you can access Presenton at: