Best models for Codex

Codex only runs OpenAI models, so the real choice is which GPT tier fits your work. Here's how the three options in the picker compare on capability and cost.

The ranking
  • 1OpenAI
    GPT-5.5OpenAIThe flagship pick for hard tasks and long agentic runs.
    Context1.05M
    Input$5/M
    CursorBench64.3%
  • 2OpenAI
    GPT-5.4OpenAIThe everyday default: strong coding at half the flagship price.
    Context1.05M
    Input$2.5/M
    CursorBench—
  • 3OpenAI
    GPT-5.4 MiniOpenAICheap and fast for routine edits and high-volume runs.
    Context400K
    Input$0.75/M
    CursorBench—
Share:
Details:

  • Agent

    Codex

  • Models

    3

  • Updated

    June 2026