diff --git a/get-started.mdx b/get-started.mdx
index aa7e3789..b334b94b 100644
--- a/get-started.mdx
+++ b/get-started.mdx
@@ -8,6 +8,24 @@ import { PodTooltip, NetworkVolumeTooltip, TemplateTooltip, PyTorchTooltip } fro
 
 Follow this guide to learn how to create an account, deploy your first GPU <PodTooltip />, and use it to execute code remotely.
 
+## Run GPU code with Flash
+
+If you want the fastest path to running GPU code on Runpod, use [Flash](/flash/overview). Flash lets you run Python functions on remote GPUs with a single decorator:
+
+```python
+import asyncio
+from runpod_flash import Endpoint, GpuType
+
+@Endpoint(name="hello-gpu", gpu=GpuType.NVIDIA_GEFORCE_RTX_4090)
+def hello():
+    import torch
+    return {"gpu": torch.cuda.get_device_name(0)}
+
+asyncio.run(hello())
+```
+
+Install Flash with `pip install runpod-flash`, authenticate with `flash login`, and you're ready to go. See the [Flash quickstart](/flash/quickstart) for complete setup instructions.
+
 ## Step 1: Create an account
 
 Start by creating a Runpod account:
@@ -189,6 +207,9 @@ runpodctl pod delete $RUNPOD_POD_ID
   <Card title="Runpod Serverless" href="/serverless/overview" icon="cloud" horizontal>
     Start building production-ready applications.
   </Card>
+  <Card title="Flash SDK" href="/flash/overview" icon="bolt" horizontal>
+    Run GPU functions with Python decorators.
+  </Card>
 </CardGroup>
 
 ## Need help?