ros/claude-code-router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add screenshot

Browse Source
This commit is contained in:
jinhui.li
2025-06-10 13:28:41 +08:00
parent ea68b2ea55
commit edc8ecbcba
2 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -50,6 +50,8 @@ You need to move them to the `$HOME/.claude-code-router/plugins` directory and c
## Some tips: ## 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. 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. 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! 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!

BIN
screenshoots/contexterror.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 48 KiB