# Add Custom Model, no model ID can be added

**URL:** <https://forum.cursor.com/t/add-custom-model-no-model-id-can-be-added/159044>\
**Category:** Bug Reports\
**Tags:** byok\
**Created:** [April 26, 2026, 12:23am UTC](https://forum.cursor.com/t/add-custom-model-no-model-id-can-be-added/159044 "2026-04-26T00:23:34Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\
**Post date:** [April 26, 2026, 8:56am UTC](https://forum.cursor.com/t/add-custom-model-no-model-id-can-be-added/159044/8 "2026-04-26T08:56:45Z")

</div>

Hey thanks for the report.

The thing is that DeepSeek V4 both `deepseek-v4-pro` and `deepseek-v4-flash` uses thinking mode, which requires returning `reasoning_content` back to the API during multi-turn tool calls. Cursor can’t do that yet, so the DeepSeek API returns this error:

```auto
The reasoning_content in the thinking mode must be passed back to the API.

```

There are already a few recent reports about this on the forum:

- [The deepseek-v4-pro api cannot be used normally](https://forum.cursor.com/t/the-deepseek-v4-pro-api-cannot-be-used-normally/159042)
- [Error when i use deepseek-v4-flash](https://forum.cursor.com/t/error-when-i-use-deepseek-v4-flash/159058)
- [DeepSeek V4: context limited to 200K + reasoning\_content error](https://forum.cursor.com/t/deepseek-v4-context-limited-to-200k-reasoning-content-error/159045)

There is also a separate feature request to add compatibility. Can you drop a like to help raise priority: [Compatibility with DeepSeek model's design to return reasoning content after tool calls?](https://forum.cursor.com/t/compatibility-with-deepseek-models-design-to-return-reasoning-content-after-tool-calls/158905)

What you can do right now:

- Community proxy. One of the users made a compatibility layer that wraps the DeepSeek API so it works with Cursor:  
[GitHub - yxlao/deepseek-cursor-proxy: Fixes reasoning\_content issue of DeepSeek V4, supprting deepseek-v4-pro and deepseek-v4-flash · GitHub](https://github.com/yxlao/deepseek-cursor-proxy)  
Run it locally, then set `Override OpenAI Base URL` to the proxy address instead of `api.deepseek.com`.

---

_[View the full topic](https://forum.cursor.com/t/add-custom-model-no-model-id-can-be-added/159044)._