Need help to conect deepseek

Support Help
1

Bug Report: Unable to connect DeepSeek as a custom model in Cursor

Steps to Reproduce (STR):

  1. API Setup: Obtained DeepSeek API keys and topped up the balance.

  2. Key Creation: Generated a new API key.

  3. Cursor Configuration: * Navigated to Cursor Settings > Models.

    • Added specific model names: deepseek-reasoner, deepseek-chat, and deepseek-r1-0528.

  4. Endpoint Configuration: Entered the following base URLs in the OpenAI-compatible section:

    • https://api.deepseek.com/v1

    • https://api.deepseek.com/beta

    • https://api.deepseek.com

Actual Result: The app constantly returns an error and fails to connect to the model.

3

You need to disable all other models when you first set it up, then turn toggle on and off custom api key when you use them.

4

Connecting to api.deepseek.com is not natively supported by Cursor, and they tend to use APIs that aren’t strict compatible with the OpenAI-compatible format we use.

You might find this project interesting! GitHub - danilofalcao/cursor-deepseek: A high-performance HTTP/2-enabled proxy server designed specifically to enable Cursor IDE's Composer to use DeepSeek's and OpenRouter's language models. This proxy translates OpenAI-compatible API requests to DeepSeek/OpenRouter API format, allowing Cursor's Composer and other OpenAI API-compatible tools to seamlessly work with these models.