Launch Composer 2.5
TL;DR
Composer 2.5 is now available, offering substantial improvements in intelligence, sustained work on long-running tasks, and more reliable instruction following. It includes updated token pricing and double usage limits for the first week.
## What changed Composer 2.5 launched on May 18, 2026. It delivers better intelligence and behavior than Composer 2, with stronger performance on long-running tasks and more reliable handling of complex instructions.
Pricing shifted to Standard mode at $0.50 per million input tokens and $2.50 per million output tokens. Fast mode, set as default, runs at $3.00 input and $15.00 output per million tokens. Double usage limits apply automatically for the first week.
## Why it matters The update focuses on sustained agent work rather than quick single-turn responses. This change supports builders who want agents to carry projects across multiple steps without frequent resets or re-prompting.
Solo operators gain a practical edge on tasks that span hours instead of minutes. The pricing structure favors selective use of Fast mode for high-value work while keeping Standard available for routine steps. Cursor is betting that improved instruction following will reduce the need for constant oversight in cloud agents.
## How to use it Open Cursor and select Composer 2.5 from the model menu. Review exact rates and limits in the model docs at cursor.com/docs/models/cursor-composer-2-5. The doubled usage window starts on the day you first access the model after May 18.
Switch modes per session based on task length and budget. Full details appear in the announcement post at cursor.com/blog/composer-2-5.
## Watch for Track whether long tasks finish with fewer manual interventions over the coming weeks. Quality drops on nuanced edge cases would undermine the reliability claim. The next logical step is tighter integration between Composer and the new multi-repo environment tools released earlier in May.
Harsh’s take
Composer 2.5 raises the cost of fast responses while promising fewer wasted turns on extended jobs. For a solo builder this means trading higher per-token spend for fewer total iterations, but only if the model actually maintains context across hours of work.
The doubled limits for one week give a short window to test real projects before the meter runs at full price. Most solo operators will still hit budget walls once the promotion ends unless they reserve Fast mode for the final assembly steps.
Test Composer 2.5 on one current multi-hour task this week and measure actual interventions required. Drop it if the error rate stays above your current baseline once limits reset.
by Harsh Desai
About Cursor
View the full Cursor page →All Cursor updatesMore from Cursor
- FeatureNew PR Review Experience and Parallel Building
Introduces a unified PR review interface with inline threads and commit history. New 'Build in Parallel' feature allows Cursor to execute independent plan tasks simultaneously using async subagents to speed up development.
- App UpdateCustomize Bugbot PR Review Effort
Admins and Individual plan users can now set Bugbot's effort level to Default, High, or Custom. High effort allows for deeper reasoning to find more bugs, while Custom effort uses natural language instructions to determine review intensity.
- IntegrationIntegrate Cursor with Microsoft Teams
Cursor is now available in Microsoft Teams. Users can mention @Cursor in any channel to delegate tasks to cloud agents, which can read thread context, select repositories, and create pull requests directly from the chat.