Cursor integration
Connect DeepSeek to Cursor with an OpenAI-Compatible Base URL
Cursor settings change over time, so verify the current model and API-key controls before rollout. The stable pieces are the Tokuse base URL, key, and DeepSeek model ID.
Settings
- Base URL
- https://tokuse.com/v1
- Model
- deepseek-flash
- Compatibility
- OpenAI-style chat completions
Setup steps
- Open Cursor Settings and find the custom model or OpenAI API configuration.
- Enter the Tokuse base URL as https://tokuse.com/v1.
- Use a Tokuse API key and keep it out of committed project files.
- Set the model name to a current Tokuse alias such as deepseek-flash.
- Run a basic read-only prompt, then test code editing with a disposable repository.
Before production use
- Keep the Tokuse key on the server or in the tool's secret store.
- Use the base URL without appending /chat/completions.
- Verify the model alias in the current Tokuse catalog.
- Test errors, timeout behavior, and cost with a small workload first.