How do I use the Wiozen API with Cursor?
Use Cursor's chat and agent models with your own key.
In short: On the Cursor Settings → Models page, enter your Wiozen key in the OpenAI API Key field, turn on Override OpenAI Base URL and enter https://api.wiozen.com/v1, then add deepseek-v4.1-flash as a custom model.
Requirements
- A Wiozen API key (
sk-gw-…). Sign-up is free; new accounts get trial credit. - An installed Cursor (code editor).
Steps
- Open the Cursor Settings → Models page.
- Paste your Wiozen key into the OpenAI API Key field.
- Turn on Override OpenAI Base URL and enter
https://api.wiozen.com/v1. - Use Add model to add
deepseek-v4.1-flash, and turn off the other models in the list. - Check the connection with the Verify button.
Things to know
- Cursor features tied to its own models, such as tab completion, do not work with a custom key. Chat and agent requests go through Wiozen.
Which model name should I enter?
Only the names on the models page are accepted. Prices per 1 million tokens are listed there too. Any other model name returns 400.
Related guides
- How do you connect an OpenAI-compatible API to a tool you already use?
- Which model should you use in Cline, Cursor, OpenCode and Aider?
- Which AI model should I choose: deciding by price, context and quality
- An AI API returns "Unknown model": where do I find the right model name?
- My AI API returns "401 Invalid API key": why isn't my key accepted?
- Why does my AI API return a 429 error, and how do I fix it?
Other guides: Cline · Roo Code · Kilo Code · Continue · Claude Code · Hermes Agent · OpenCode · Aider · Qwen Code · Open WebUI · LibreChat · AI Engine