DEVSAIO

Use your own API key in Cursor (custom OpenAI base URL)

How to add a custom OpenAI-compatible endpoint in Cursor, which features use it, and how to add models like Claude and Gemini.

DEVSAIO team · 2 min read
Share on X

Cursor lets you bring your own API key and override the OpenAI base URL. That lets you use models from DEVSAIO in Cursor's chat.

Setup

  1. Open Cursor Settings → Models.
  2. Under API Keys, paste your DEVSAIO key into the OpenAI API Key field.
  3. Turn on Override OpenAI Base URL and enter https://devsaio.lol/v1.
  4. Click Verify.
  5. In the model list, click Add model and type the exact model id, for example claude-sonnet-4-6 or gemini-3.5-flash.
  6. Select that model in the chat panel.

What uses your key

Cursor's own built-in features (such as Tab completion and some agent features) run on Cursor's infrastructure and may not use a custom key. Chat with a model you added manually goes through your endpoint. Cursor changes these rules from time to time, so check their documentation if something doesn't route the way you expect.

Tip: If Verify fails, make sure the base URL ends with /v1 and that the key has balance and no exhausted monthly limit.

Which models to add

  • claude-sonnet-4-6 for everyday coding
  • gpt-5.6-luna as a second opinion
  • gemini-3.5-flash when you paste very large files

Usage from Cursor appears in Usage Logs like any other request.

Try it with one API key

Claude, GPT, Gemini, DeepSeek, image and video models through one OpenAI- and Anthropic-compatible endpoint. Prepaid, pay only for what you use.

Keep reading