Codex Plus Plan: Use Luna and Save Sol and Astra
Melvin Vivas · X post · 2026-09-05 · Open on X
Topics: AI Dev Tools & Productivity, LLM Fundamentals · Level: beginner
Summary
The creator argues that on the $20 Codex Plus plan, Sol and Astra burn through usage too fast to be practical. Luna should be the default model there. He likes Sol and Astra for speed, but heavy use of them needs a bigger plan like Codex Pro.
Key points
- Sol and Astra are very capable but expensive in usage.
- The $20 Codex Plus plan does not go far with Sol or Astra.
- Plus users should use Luna as the default model.
- Sol and Astra get things done fast, so they are still worth it on a higher plan.
- He plans to upgrade to Codex Pro after rebalancing his AI subscriptions.
Resources mentioned
- OpenAI Codex · tool · openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
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: Developers moving from ChatGPT/Codex to Claude (Melvin Vivas on X · notes), Creator Opinion: Codex Is Still the Best at Computer Use (Melvin Vivas on X · notes), OpenAI Codex Ambassador applications are open (Melvin Vivas on X · notes), GPT-Live-1.1: Multilingual Voice Update for ChatGPT and Codex (Melvin Vivas on X · notes) and 264 more - Luna · tool · openai.com · paid
The other model/agent the classifier routes tasks to; the post doesn't describe it further.
Also in: GPT-6.1 Sol May Beat Luna for Subagents (Melvin Vivas on X · notes), Picking models for orchestrator and subagent roles in Codex (Melvin Vivas on X · notes), GPT-6 Sol Ultra Subagents Use Up Limits Fast (Melvin Vivas on X · notes), GPT-6 Sol vs Opus 5.5 in a Livestream Comparison (Melvin Vivas on X · notes) and 14 more - GPT 5.6 Luna · tool · openai.com · paid
The OpenAI model used inside Codex for the demo. The transcript gives the variant name as 'Soul', which is unclear.
Also in: Set Codex subagent model and reasoning to save usage limits (Melvin Vivas on X · notes), Use GPT-5.6 Luna in Codex for Terminal Tasks (Melvin Vivas on X · notes), Match Reasoning Effort to Task Length in Codex (Astra/Sol) (Melvin Vivas on X · notes), Run Coworker desktop agents cheaply with GPT-5.6 Luna on OpenRouter (Melvin Vivas on X · notes) and 24 more - GPT-6 Astra · tool · openai.com · paid
The model announced in the quoted launch post, pitched as the developer's most capable model for work, coding, science and cybersecurity, and able to operate a computer.
Also in: Glimpse: A Visual Reasoning Model That Uses a Visual Scratch Space (Melvin Vivas on X · notes), Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), GitHub Copilot Adds Intelligent Local Model Routing (Project HydraFusion) (Melvin Vivas on X · notes), Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter (Melvin Vivas on X · notes) and 55 more
Try this
- On Codex Plus, use Luna as your default model.
- Upgrade to a higher plan if you need heavy use of Sol or Astra.
More in AI Dev Tools & Productivity
- Inspect Codex Traces with jsonl-viewer
- Codex Agent Command Center: the `codex agents` Command
- Match Model and Reasoning Level to Task Complexity in Coworker
- Luna, Not Sol, as the Daily Driver on Codex Plus
- Launching Cursor Coding Tasks from Grok Bot
- Using Grok Bot as a Gmail Auto-Reply and Monitoring Assistant