---
title: "GPT-5 is now available in Cursor"
description: "Cursor has made OpenAI’s GPT-5 available to users, presenting it as a coding-focused model based on an initial internal evaluation. Five engineers report using it for long-running tasks with Background Agents, parallel foreground agents, complex debugging, and Stripe-query latency optimization, while noting that explicit instructions improved its steerability. One engineer adjusted GPT-5’s verbose default style and follow-up behavior through rules. In a monorepo with separate frontend and backend submodules, GPT-5 built a backend API endpoint and corresponding React component, regenerated protobufs, and corrected resulting type errors in one shot. During launch week, paying users receive free credits, and the announcement characterizes GPT-5 as well suited to coding and tool calling."
---

# GPT-5 is now available in Cursor

[Cursor](https://yomu.fyi/company/cursor) · Aman Sanger · Aug 7, 2025

**Type:** Announcement

## Summary

Cursor has made OpenAI’s GPT-5 available to users, presenting it as a coding-focused model based on an initial internal evaluation. Five engineers report using it for long-running tasks with Background Agents, parallel foreground agents, complex debugging, and Stripe-query latency optimization, while noting that explicit instructions improved its steerability. One engineer adjusted GPT-5’s verbose default style and follow-up behavior through rules. In a monorepo with separate frontend and backend submodules, GPT-5 built a backend API endpoint and corresponding React component, regenerated protobufs, and corrected resulting type errors in one shot. During launch week, paying users receive free credits, and the announcement characterizes GPT-5 as well suited to coding and tool calling.

## Context

The announcement shares an initial internal evaluation of GPT-5 by five engineers, focused on its effectiveness for coding, complex tasks, debugging, and tool calling.

## Approach / What changed

GPT-5 is integrated into Cursor and used with Background Agents, parallel foreground agents, rules for response behavior, and coding tasks spanning separate frontend and backend submodules. The evaluation records engineers’ observations and examples, including protobuf regeneration.

## Takeaways

- GPT-5 was used for long-running work with Background Agents and parallel foreground agents, including independent tasks and reviewing outputs.
- Explicit instructions improved steerability; rules were used to make responses more concise and reduce follow-up questions.
- GPT-5 produced a backend API endpoint and corresponding React component across separate monorepo submodules, then regenerated protobufs to fix type errors in one shot.

**Tags:** [Cursor](https://yomu.fyi/topic/cursor), [LLMs](https://yomu.fyi/topic/llm)

- Source: [Cursor](https://cursor.com/blog/gpt-5)
- Source URL: https://cursor.com/blog/gpt-5
- Ingested by Yomu: 2026-09-02T11:45:42.604Z

[Read original post](https://cursor.com/blog/gpt-5)