Blog

Grok 4.6 is a frontier model from Cursor and SpaceXAI for complex coding and knowledge work. It builds on Grok 4.5 with improved instruction following and long horizon agentic work.

We recommend using Grok 4.6 for improved instruction following and long horizon agentic work. Grok 4.5 remains available.

We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.

We recommend using GPT 5.3 Codex. It's faster than previous generations and more cost effective.

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

GPT 5.6 Terra is the mid tier model in OpenAI's GPT 5.6 family. It sits between Sol and Luna on intelligence and price, making it a strong pick for everyday agentic coding when you want more capabilit

GPT 5.6 Sol is OpenAI's flagship GPT 5.6 model in Cursor. It is the strongest of the Sol, Terra, and Luna family: persistent on long running agent work, fast enough for interactive sessions, and notab

GPT 5.6 Luna is the smallest and lowest cost model in OpenAI's GPT 5.6 family. Use it for high volume, latency sensitive, or cost sensitive agent work where Sol or Terra would be more than you need.

GPT 5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long running work and stays on task for significantly longer before stopping early, which matters most in complex, multi step

GPT 5.4 Nano is the smallest and fastest model in the GPT 5.4 family. At $0.20 per million input tokens, it's built for high volume workloads where speed and cost matter more than peak reasoning. Reac