Did I encounter a token usage error with Cursor? I’ve been using Grok 4.6 recently, and its usage has always been counted under the Cursor model statistics. Previously, when I used the DeepSeek model via API, its usage was categorized under “Other models,” and the same happened when I used GPT models. So I always assumed that the quotas for the Cursor model and Other models were independent of each other. But just now, I found that after exhausting the Cursor-Grok-4.6 quota, the Other models were also disabled. Is this a bug? Because previously, Composer 2.5 was billed independently from the other models.
Hey, thanks for the detailed report. This isn’t a bug. It’s expected behavior, but I agree it’s not obvious.
Your two pools aren’t fully independent:
- Named third-party models (DeepSeek, GPT, etc.) only pull from the Other Models pool.
- Cursor models (Auto, Composer, Cursor Grok) use the Cursor Models pool first, and when it’s used up they automatically continue from the remaining Other Models pool.
That’s what happened here. Heavy Grok 4.6 usage first drained your Cursor Models quota, then it spilled over and finished off Other Models too. That’s why both show exhausted. Before, Composer 2.5 looked like it was billed separately just because you never fully used up the Cursor Models pool, so the spillover never kicked in.
This two-pool behavior is described here: Models & Pricing | Cursor Docs
What you can do now: your quotas will reset at the start of the next billing cycle (you can see the exact date in the dashboard), or you can enable on-demand usage in settings to keep going until the reset.
Related threads if you want to dig deeper:
- Custom model usage keeps rising when exclusively using Grok or Composer
- Cannot use Auto after Included Usage reaches 100%
Let me know if anything’s still unclear.