Model choice in Codex: GPT-6.1 Sol over Astra
Melvin Vivas · X post · 2026-10-04 · Open on X
Topics: AI Dev Tools & Productivity · Level: beginner
Summary
The creator no longer uses Astra in Codex. He finds GPT-6.1 Sol good enough for his work, and it uses up less of his usage limits. It's a quick practical tip on picking models in a coding assistant.
Key points
- In Codex, GPT-6.1 Sol is good enough for the creator's daily coding work.
- GPT-6.1 Sol uses less of the usage limits than Astra.
- Picking a cheaper model that is good enough helps you stay within usage 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-6.1 Sol · tool · openai.com · paid
A new OpenAI model announced at DevDay 2026 (name as written in the machine transcript), offered with Fast and Ultra fast speed tiers.
Also in: Why Model Speed Matters in Coding Agents: Codex vs ChatGPT Plans (Melvin Vivas on X · notes), Liquid AI's d1 Decision Model Now Accepts Images (Melvin Vivas on X · notes), OpenAI Makes GPT-6 Astra and GPT-6.1 Sol About 50% Faster (Melvin Vivas on X · notes), Is Codex Pro Worth It? Buy for Usage, Not for Dots (Melvin Vivas on X · notes) and 14 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
- Try GPT-6.1 Sol as your default model in Codex to save usage limits.
More in AI Dev Tools & Productivity
- Avoid Grok Bot Group Chats: They Burn Through Token Limits
- Grok Bot That Finds X Posts Giving Away Free AI Credits
- Pi can't use Claude Code plans: it needs topped-up API credits
- Clone Your Voice from a Short Clip with Chatterbox TTS
- Coworker v0.7.1 Release: Custom Bot Avatars and Update Checks
- Cursor /visualize: Build Charts and Diagrams Inline in the Agent Chat