From 4f91a5c8a861c70fa60aa8a39fc7e9d567201fb1 Mon Sep 17 00:00:00 2001
From: Toray Altas <6816042+taltas@users.noreply.github.com>
Date: Tue, 21 Jul 2026 00:06:05 +0000
Subject: [PATCH] docs(deepseek): note image input support for V4 models

---
 docs/providers/deepseek.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/providers/deepseek.md b/docs/providers/deepseek.md
index f62253bd..f45b13b7 100644
--- a/docs/providers/deepseek.md
+++ b/docs/providers/deepseek.md
@@ -47,4 +47,5 @@ For the complete, up-to-date model list, see [DeepSeek's API documentation](http
 ---
 
 ## Tips and Notes
+*   **Image Input:** `deepseek-v4-pro` and `deepseek-v4-flash` support image (vision) inputs, so you can attach images in chat when using these models. The legacy `deepseek-chat` and `deepseek-reasoner` aliases do not support images.
 *   **Pricing:** Refer to the [DeepSeek Pricing](https://api-docs.deepseek.com/quick_start/pricing/) page for details on model costs.