Set Codex subagent model and reasoning to save usage limits
Melvin Vivas · X post · 2026-09-25 · Open on X
Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP, LLMOps, Deployment & Monitoring · Level: intermediate
Summary
A practical tip for people using the Sol or Astra models in OpenAI Codex. Set the model and reasoning level for each subagent on purpose, so subagents don't use your usage limits too fast.
Key points
- When you use Sol or Astra in Codex, set the subagent's model yourself instead of relying on defaults.
- Also set the subagent's reasoning level (effort).
- Choosing cheaper models or lower reasoning for subagents helps you avoid using up your plan limits.
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 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: 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), Codex Config: GPT-6 Astra Orchestrator + GPT-5.6 Luna Subagents at Medium (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
- In Codex, set each subagent's model and reasoning level so you don't use up your usage limits.
More in AI Dev Tools & Productivity
- Example DeepWiki: Auto-Generated Docs for a Colab Notebooks Repo
- Generate Instant Repo Documentation for Free with DeepWiki
- Windsurf Split: Google Antigravity, Cognition's Devin & AI Coding Tools
- Streamer Suite: livestream overlay app built live with Claude Code
- A Cheaper Voice Option Than ElevenLabs, Credited to @thorwebdev
- Using Devin CLI with the free SWE-2 model for sysadmin tasks