One dev's real-world comparison of 4 AI coding subscriptions
A user shares hands-on experience running four AI coding side by side: Cursor at $20/month, Claude Code at $20/month, Codex at $20/month, and Opencode at $10/month. Cursor's monthly rather than on a rolling window, so there's no sudden 5-hour or weekly cutoff, and its in-house models have caught up to top-tier , making it the strongest all-around pick. Its model delivers 400 million tokens per month for $20, well-suited for quick edits and work, and can be paired with the newer Grok 4.5 model for planning.
The $20 plan is recommended for most users. For Claude Code, the Fable 5 model was still available at the time of writing (until July 12), and it excels at planning, reading existing code, and fixing awkward UI issues. Its limits skew toward a smaller , but that appears to translate into a larger overall weekly allowance — a frequent point of comparison against Codex, which is known for confusing limits.
Claude Code also performs well for design and research work and collaborative sessions, though it hard-stops mid-task once limits are hit.
Key points
- Cursor ($20): monthly, avoiding sudden 5-hour or weekly cutoffs
- Cursor's model offers 400M tokens/month for $20, good for quick edits
- Cursor can pair Grok 4.5 as a planner; the $20 plan is recommended for most users
- Claude Code had the Fable 5 model available until July 12 at time of writing, strong for planning, code reading, and UI fixes
- Claude Code's is smaller but yields a larger weekly total; it hard-stops mid-task once limits are reached