Superconductor Docs

Codex

Superconductor is the best place to run Codex in the cloud.

Codex model selection showing GPT-5.6 Sol, Terra, and Luna at Medium, High, Extra High, and Max reasoning, followed by GPT-5.5

Credentials

Superconductor supports two ways to authenticate Codex:

  • ChatGPT plan: Connect your ChatGPT account via OAuth in your Account, Project, or Workspace settings. Your connected plan is used when you launch an implementation directly. Any tier can connect, including free and Go, but the models you get depend on your plan — see Availability.
  • API Keys: Configure your OpenAI API key at the Project or Workspace level. Used when a connected ChatGPT plan isn't available for the launch.

See Agent credentials for details on precedence rules.

Models

Codex supports the following models:

  • GPT-5.6 Sol - The most capable GPT-5.6 option for complex coding, reasoning, and polish. Used first in Superconductor's best available credential fallback.
  • GPT-6 Astra - OpenAI's newest model for complex coding, reasoning, and multi-step work.
  • GPT-5.6 Terra - A balanced GPT-5.6 option for everyday coding work where you want strong capability with lower cost than Sol.
  • GPT-5.6 Luna - The fastest and most cost-efficient GPT-5.6 option for simpler or high-volume work.
  • GPT-5.5 - OpenAI's previous-generation coding model. You can pick it explicitly on an implementation, or set it as your Default agent profile.

Codex models support configurable reasoning effort levels. Each level appears as a separate selectable profile.

ModelReasoning levels
GPT-6 AstraMedium, High, Extra High, Max
GPT-5.6 Sol, Terra, and LunaMedium, High, Extra High, Max
GPT-5.5Medium, High, Extra High

What are reasoning effort levels? Reasoning effort controls how much computation the model uses when thinking through a problem. Medium offers a good balance of speed and quality for most tasks. High increases deliberation time for better results on harder problems. Extra High and Max push deliberation further still, producing the best results for complex tasks but with higher cost and latency.

Learn more about OpenAI models in the OpenAI model guide.

Availability

Free and Go ChatGPT plans can't run Astra, Sol, or Luna. If you connect a free or Go ChatGPT account, Codex only gives you GPT-5.6 Terra. GPT-5.5 is a legacy model and also needs Plus or above. To run Astra, Sol, Luna, or GPT-5.5 on a connected plan, use ChatGPT Plus, Pro, Business, or Enterprise — or add an OpenAI API key instead, which works with every model.

OpenAI's Codex model guide describes Astra, Sol, Terra, and Luna and notes which plans can use them in Codex. See OpenAI's Codex model documentation for current availability.

Usage stats

If you've connected your ChatGPT plan, Superconductor shows your rate limit utilization next to the agent name. Plus shows two numbers, 5h and 7d, while Pro shows a single 7d. See Usage stats for details.

On this page