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.

Strengths

  • Handles long-running tasks that require using tools, checking results, and adjusting its approach.
  • Works across code, documents, spreadsheets, and PDFs.
  • Follows detailed instructions more reliably than Grok 4.5.

Effort levels

Grok 4.6 supports four effort levels: xhigh, high (default), medium, and low. Higher effort gives the model more time to work through difficult tasks.

Fast is the default speed tier on Pro and higher plans. On the Start plan (India only), Grok 4.6 is fixed at medium effort at standard speed.

Tools

Grok 4.6 has access to all agent tools when used with Cursor, including:

Learn more about how tools work and tool calling fundamentals.

Pricing

Grok 4.6 is part of the Cursor Models pool on individual and team plans. This pool also includes Grok 4.5 and Composer 2.5.

Standard on-demand usage is priced at $2/M input tokens, $0.50/M cached input tokens, and $6/M output tokens. The Fast variant is priced at $4/M input tokens, $1/M cached input tokens, and $12/M output tokens. All prices are per million tokens.