From ceb4890ca3651899dd3e2b1564168ab098ac540d Mon Sep 17 00:00:00 2001
From: Deven Navani <4031146+devennavani@users.noreply.github.com>
Date: Thu, 30 Jul 2026 11:29:32 -0700
Subject: [PATCH] docs: add Modal provider setup (#39710)

---
 packages/web/src/content/docs/providers.mdx | 24 +++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/packages/web/src/content/docs/providers.mdx b/packages/web/src/content/docs/providers.mdx
index d3c541311f..7931d4e03f 100644
--- a/packages/web/src/content/docs/providers.mdx
+++ b/packages/web/src/content/docs/providers.mdx
@@ -1505,6 +1505,30 @@ To use Kimi K2 from Moonshot AI:
 
 ---
 
+### Modal
+
+1. Create a [shared Endpoint](https://modal.com/endpoints) for the model you want to use.
+
+2. Create a [proxy token](https://modal.com/docs/guide/endpoints#proxy-tokens), then join its ID and secret with a period:
+
+   ```txt
+   wk-<id>.ws-<secret>
+   ```
+
+3. Run the `/connect` command, search for **Modal**, and enter the combined proxy token.
+
+   ```txt
+   /connect
+   ```
+
+4. Run the `/models` command to select one of the endpoints in your Modal workspace.
+
+   ```txt
+   /models
+   ```
+
+---
+
 ### NVIDIA
 
 NVIDIA provides access to Nemotron models and many other open models through [build.nvidia.com](https://build.nvidia.com) for free.