Cursor adds Claude Haiku 5.5 to its model picker
Cursor’s model documentation lists Claude Haiku 5.5 as available through Cursor Settings → Models. It gives the model a 300,000-token context window and says it supports context windows up to 1 million tokens.
For requests with up to 100,000 input tokens, the listed rates are $0.10 per million input tokens and $0.50 per million output tokens. Requests above 100,000 input tokens are billed at five times those rates: $0.50 per million input tokens and $2.50 per million output tokens. Cursor also reports a 48.4% CursorBench score at maximum effort; this is the platform’s own reported benchmark result.