Save Codex Usage Limits by Routing Tasks Between Two Models
Melvin Vivas · X post · 2026-09-14 · Open on X
Topics: AI Dev Tools & Productivity, LLMOps, Deployment & Monitoring · Level: beginner
Summary
A tip for stretching Codex usage limits: open separate chats with two models. Send complex or large tasks to Astra and small or minor tasks to Luna.
Key points
- Open several Codex chats, each using a different model.
- Send complex or large tasks to the stronger model (Astra).
- Send small or minor tasks to the lighter model (Luna) to save usage limits.
- More generally, match model size to task difficulty to control cost and quota.
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 - 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 - 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
Try this
- Open separate Codex chats with Astra and Luna.
- Send big or complex tasks to Astra and small tasks to Luna to save usage limits.
More in AI Dev Tools & Productivity
- Using Codex to Find and Visualize Disk Usage in the Terminal
- Codex Computer Use with Astra for Human-Like App Testing
- Paste Documentation URLs into Codex Instead of Using MCP
- Livestream: Building a React Native ChatGPT App with Cursor and OpenAI
- Use Codex for Quick Everyday Tasks Like Resizing Images
- Track your Codex usage limits with CodexBar