Composer 2.5 is Cursor's own agentic model. It builds on [Composer 2](/blog/composer-2) with stronger intelligence on long agentic tasks, better effort calibration, tool selection, intent understanding, and reliability.

## Strengths

- Strong on long-horizon tasks via [reinforcement learning](/blog/real-time-rl-for-composer) on [long-horizon coding tasks](/blog/self-driving-codebases).
- Default fast variant for interactive sessions; standard tier further optimized for cost per token.
- Tuned for tool use, file edits, and terminal operations inside Cursor.

## Tools

Composer 2.5 has access to all agent tools when used with Cursor including:

Learn more about [how tools work](https://cursor.com/docs/agent/overview.md#tools) and [tool calling fundamentals](https://cursor.com/learn/tool-calling.md).

## Pricing

A **faster variant** with the same intelligence is also available at $3/M input and $15/M output tokens. Fast is the default in the product and is priced lower than other fast models at similar speeds.

Composer 2.5 draws from the weekly pool of [Cursor models](https://cursor.com/docs/models-and-pricing.md#cursor-models) included with every paid plan, alongside Grok 4.7, Grok 4.6, and Grok 4.5. On [legacy Cursor plans](https://cursor.com/docs/account/pricing/legacy-cursor-plans.md), it draws from the monthly Cursor Models pool. Additional usage beyond the pool is charged at the rates below. All prices are per million tokens.


---

## Sitemap

[Overview of all docs pages](/llms.txt)
