Cursor Token Rate now applies only to eligible third-party models
On Teams and Enterprise, the $0.25 per million token Cursor Token Rate is charged on eligible third-party models only. Low-cost models such as Claude Haiku 5.5, Gemini Flash models and GPT Mini/Nano models are excluded.
Details
- The rate applies on top of model API pricing for additional usage and BYOK usage, to input, output and cached tokens.
- It applies when you pick an eligible third-party model directly and when Cursor Router (Balance or Intelligence) routes to one.
- Excluded: Claude Haiku 5.5, Gemini 2.5/3/3.7/3.8 Flash, Gemini 3.1/3.5 Flash Lite, GLM 5.3 Flash, GPT-4.1 Nano, GPT-4o Mini, GPT-5 Mini, GPT-5.1 Codex Mini, GPT-5.4 Mini/Nano and GPT-5.6 Luna.
- Cursor models (Grok, Composer), Cost mode requests and individual plans don't pay it.
Sources
Get pricing-change alerts
Email me when Cursor, Claude, Codex or Copilot change prices or limits. No spam, roughly 1–4 emails a month.
We only use your email for these alerts — never sold or shared. Stored on Cloudflare. See our privacy note.