diff --git a/README.md b/README.md
index e12a709..15adf43 100644
--- a/README.md
+++ b/README.md
@@ -50,6 +50,8 @@ You need to move them to the `$HOME/.claude-code-router/plugins` directory and c
 ## Some tips:
 If you’re using the DeepSeek API provided by the official website, you might encounter an “exceeding context” error after several rounds of conversation (since the official API only supports a 64K context window). In this case, you’ll need to discard the previous context and start fresh. Alternatively, you can use ByteDance’s DeepSeek API, which offers a 128K context window and supports KV cache.
 
+![](screenshoots/contexterror.jpg)
+
 Note: claude code consumes a huge amount of tokens, but thanks to DeepSeek’s low cost, you can use claude code at a fraction of Claude’s price, and you don’t need to subscribe to the Claude Max plan.
 
 Some interesting points: Based on my testing, including a lot of context information can help narrow the performance gap between these LLM models. For instance, when I used Claude-4 in VSCode Copilot to handle a Flutter issue, it messed up the files in three rounds of conversation, and I had to roll everything back. However, when I used claude code with DeepSeek, after three or four rounds of conversation, I finally managed to complete my task—and the cost was less than 1 RMB!
diff --git a/screenshoots/contexterror.jpg b/screenshoots/contexterror.jpg
new file mode 100644
index 0000000..4abcd55
Binary files /dev/null and b/screenshoots/contexterror.jpg differ