How to add a custom model like DeepSeek-V3 (which is OpenAI compatible)

I am starting to love you all!!! Deepseek is doing the entire world a favor giving everyone access to ai. Please allow them to be all they can!!!

2 Likes

You knowā€¦ You know you knowā€¦ Itā€™s the best there is and relatively speaking (Claude) it costs you a penny on the dollar. OpenAI just started a ā€œfreeā€ competitorā€¦ Please donā€™t do that to us. I already know it will be throttled to promote their premium$$$.

I think I saw that. And itā€™s causing people to think deepseek is slow. Fireworks is slow. Deepseek is very fast, very very very accurate, and relatively speaking, 10^2 cheaper.

How do people say: if itā€™s free youā€™re the product :wink:

Deepseek is Chinese and they always were popular for data collection (look at TikTok). So be careful with it, you never know what they do with this data behind the scenes. Obviously we donā€™t know what other West providers do with the data, but somehow I trust West more. Ideally all models have to be run locally for the best privacy.

Just sayin. Iā€™m using it myself and I love it, but I tend to avoid sharing any sensitive data to it. Especially my codebase.

Thanks man! It works

@hideInEye You can follow this DeepSeek official document(https://api-docs.deepseek.com/) to setup in Cursor. You need to add the deepseek API Key and the API url in the blank of ā€œOpenAI API Keyā€. Then disable other models, apply and it will work.

Lmaoā€¦ You can download it all and dissect it. Cursor has all your data :slight_smile:

is this still working?