Watching Codex weekly limits: GPT 5.6 Sol vs Luna max cost
Melvin Vivas · X post · 2026-08-17 · Open on X
Topics: AI Dev Tools & Productivity, LLMOps, Deployment & Monitoring · Level: beginner
Summary
The creator watched his Codex weekly usage limit drop quickly during normal prompting on a small codebase, and blames the expensive GPT 5.6 Sol model. He plans to switch to the Luna max model to make his limits last longer. The lesson: which model you pick strongly affects how fast you use up your plan.
Key points
- Codex shows your weekly usage limit, and you can watch it go down as you prompt.
- GPT 5.6 Sol (the top model) uses up limits fast, even on a small codebase.
- Switching to a cheaper model (Luna max) makes your weekly limit last longer.
- The best model isn't always needed. Match the model to the task to control cost.
Resources mentioned
- OpenAI Codex · tool · openai.com · paid
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more - GPT 5.6 Sol · tool · openai.com · paid
A GPT-family model available through an API, whose API and credit pricing was cut by over 20% for three months.
Also in: Creator's Top 3 Closed Models: Fable 5, GPT 5.6 Sol, Grok 4.6 (Melvin Vivas on X · notes), Coworker v0.3.1: Telegram Streaming Sync, Built Fast with Codex (Melvin Vivas on X · notes), Coworker: Open-Source Grok Bot Clone Built on Pi and CopilotKit (Melvin Vivas on X · notes), GPT 5.6 Sol (medium) in ChatGPT for planning tasks (Melvin Vivas on X · notes) and 12 more - Luna max · tool · developers.openai.com · paid
The model the creator ran in Codex for this test; the post presents it as not the smartest option.
Also in: Debug Animated UI Bugs by Having Codex or Claude Code Watch a Screen Recording (Melvin Vivas on X · notes)
Try this
- Check your Codex weekly limit while you work.
- Use a cheaper model like Luna max for routine tasks and keep Sol for hard problems.
More in AI Dev Tools & Productivity
- Use GPT 5.6 Luna Instead of Sol to Make Codex Limits Last
- Cursor Phone-to-Cloud-to-Local Agent Workflow
- Running Codex with DeepSeek V4 Flash through OpenRouter
- Codex tip: use /feedback to report fast usage-limit burn
- Handing off an unfinished Codex session to Grok Build
- Grok Build finishes a task Codex left hanging