OpenLuxUse OpenLux models inside Cursor
Cursor accepts a custom OpenAI-compatible endpoint. Paste your OpenLux key, override the base URL and Cursor chat can run on any model in the catalogue — GPT-6 Astra, Claude Sonnet 4.5, DeepSeek V4 — at OpenLux rates.
Set it up in four steps
Create an OpenLux key
Open the console, create an API key and copy it. Trial credit is enough to test Cursor-side chat for days.
Open Cursor model settings
In Cursor, go to Settings → Models and enable the OpenAI API key section, then paste your OpenLux key.
Override the base URL
Turn on the base-URL override and enter https://openlux.lol/v1. Use Add model to add catalogue names such as gpt-6-astra.
Verify and chat
Select the model in Cursor chat. If a request fails, check the key and confirm the model name matches the catalogue exactly.
Configuration
Copy these blocks, replace the placeholder key and you are done.
Cursor settings
OpenAI API key: sk-openlux-...
Override base URL: https://openlux.lol/v1
Model: gpt-6-astraModels that fit Cursor
GPT-6 Astra
OpenAI · $0.3677 / 1M tokens
Claude Sonnet 4.5
Anthropic · $0.2647 / 1M tokens
Gemini 3.8 Flash
Google · $0.0551 / 1M tokens
DeepSeek V4
DeepSeek · $0.0613 / 1M tokens
The full list is in the model catalogue and the use-case collections.
Cursor + OpenLux questions
Which Cursor features work with a custom base URL?
Chat and agent requests route through the custom endpoint. Cursor's own Tab completion and built-in models run on Cursor's infrastructure and are unaffected, so the override is safe to try.
Which models should I pick in Cursor?
gpt-6-astra or claude-sonnet-4-5-20250929 for editing and agents, gemini-3.8-flash for large-volume chat, deepseek-v4 when you want the lowest per-token cost.
Why use OpenLux instead of Cursor's built-in models?
Same editor, different meter: OpenLux rates run up to 96% below official model pricing and cover many providers on one key and one invoice, so experimenting across models does not multiply accounts.
Do I have to remove my existing Cursor models?
No. The override applies to the OpenAI-compatible path only; keep the default models and switch per chat as you like.
How much will this cost?
Estimate Cursor API cost
Separate the Cursor plan from routed custom-endpoint usage.
Open the cost guideAdd AI review to the pull-request loop
Build a bounded code reviewer
Use the same OpenAI-compatible endpoint to review pull-request diffs, publish findings and estimate the review budget.
Open the AI code review guideConnect Cursor to OpenLux today
One key covers every model in this guide and the rest of the catalogue, metered in USD with free trial credit to start.