I use my own API key, but the actual usage is still counted under “Other Models.” As a result, when the usage limit for “Other Models” is reached, I can no longer use my own API key.
Steps to Reproduce
Cursor Settings > Models, set “OpenAI API Key” to my own API key, enable “Override OpenAI Base URL,” refer to the image “模型自定义截图.png”
Expected Behavior
On the usage statistics page of the dashboard, the models under my own API key are also counted under “Other Models.” If the usage of “Other Models” has not reached the limit, no issues arise. However, once the usage limit is reached, I am unable to even use my own API key. Refer to the image “用量异常截图.png”
This issue is actually mentioned in your official documentation, which states that when using your own API key, it will not consume the quota. Refer to the image “额度不限制截图.png”
This is actually expected behavior on Teams and Enterprise plans, and I can see why the docs made it look otherwise. Here’s what’s going on:
On Teams/Enterprise plans, third-party models carry a Cursor Token Rate of $0.25 per million tokens, and that applies to models you run with your own API key too (BYOK or not). The actual model cost still goes to your own provider account, but the Cursor Token Rate is real usage, so your own-key requests appear under Other Models and draw from your included Other Models allowance. Once that allowance is used up, further requests, including your own-key ones, get paused.
The line you screenshotted (“unlimited AI messages at your own cost”) holds for individual (Pro) plans, where there’s no Cursor Token Rate on BYOK. On Teams/Enterprise it’s incomplete, since the Cursor Token Rate does count. I’ll get that page clarified.
To get unblocked: on Teams, on-demand usage is what lets requests continue past the included allowance. If your own-key requests are hard-stopping, a team admin should check two things in the dashboard:
On-demand usage is enabled for the team
The team’s monthly spending limit hasn’t been reached (and raise it if needed)
With on-demand on, your own-key requests keep flowing and you’re only billed the Cursor Token Rate ($0.25/M tokens), not the full model cost.
Thank you for your reply. Am I understanding correctly that when I use my own API key, it will consume the tokens of the model in my own API key as normal, as well as a small amount of Cursor’s “Other Models” quota?
