Cursor 如何接入 MiniMax-M2.7：Ungate 扩展解决推理与回复混流问题

MiniMax-M2.7 is a new Chinese frontier model from MiniMax. According to some benchmarks, it has almost caught up with Opus-4.6. However, based on my tests over the past few days, I’ve concluded that it doesn’t even measure up to Sonnet-4. If you use it for simple tasks, everything is fine. But if you have a monorepo project structure with packages and apps, you have to run a lot of iterations to complete tasks.

But you need to consider not only quality and speed, but also price. MiniMax is 10 times cheaper than Sonnet-4.7. A $10 subscription gives you 1,500 requests every 5 hours and 15,000 requests per week. Therefore, for simple tasks or situations where speed isn’t a priority, MiniMax can be a reasonable choice.

The documentation on the MiniMax website states that the model uses the OpenAI format and is compatible with most IDEs. But it turned out that if you connect it to Cursor, it doesn’t separate the contents of <think>...</think> from the actual response; everything goes into a single stream. You see the model’s thoughts and the response mixed together, and at some point it becomes unclear where its thoughts end and the response to the user begins. Working in this mode is extremely inconvenient.

I’ve added MiniMax support to the Ungate extension for Cursor that I’m developing. It processes content from <think>...</think> blocks, and now Cursor correctly separates the model’s reasoning from the response to the user. Working with MiniMax in Cursor is now the same as with other OpenAI-compatible models.

To access the model, you need to add the custom model name MiniMax-M2.7 to Cursor. I’ve added a Base URL selector for MiniMax to the Ungate settings: China, Global, Custom.

GitHub: https://github.com/orchidfiles/ungate

Nice!

That’s something what makes me a little confused regarding the benchmarks like SWE-bench etc. Having extra cheap model means you can achieve the same relatively to the expensive models with simply 10-20x more queries in the loop. So it might be a good option for automations running in the background every day on routine tasks. With the same outcome.