Set up DeepSeek in Cursor

Before you start

• An API Store account with some balance
• An API key from the API keys page (it starts with sk-)

Steps

1. Open Cursor, then Settings, then Models.
2. In the OpenAI section, paste your API Store key into OpenAI API Key.
3. Turn on Override OpenAI Base URL and enter the base URL below.
4. Choose Add model, type the model name below and switch it on.
5. Press Verify, then pick the model in the chat panel.

Menu names can differ slightly between versions of the app.

Which model to pick

• deepseek-v4-1-flash for everyday coding and chat
• deepseek-v4-1-flash-economy when the lowest price matters most

Troubleshooting

• 401 invalid_api_key. The key is wrong or revoked. Create a new one.
• 402 insufficient_balance. Top up, or raise the key's daily cap.
• 404 model_not_found. Check the spelling of the model name.
• Cursor's own models stop working. The base URL override applies to all OpenAI models in Cursor. Turn it off to go back.

What it costs

deepseek-v4-1-flash: $0.21 input and $0.84 output per 1M tokens in peak hours, $0.105 and $0.42 off-peak. Input read from cache costs $0.0042.

All prices →