Codex
Superconductor is the best place to run Codex in the cloud.
Credentials
Superconductor supports two ways to authenticate Codex:
- ChatGPT Pro Plan: Connect your OpenAI account via OAuth in your Account, Project, or Workspace settings. Your connected plan will be used for implementations you launch directly.
- API Keys: Configure your OpenAI API key at the Project or Workspace level. API keys are required for automatically triggered implementations (e.g., external PRs, PRs created from Slack, or Email triage).
See Agent credentials for details on precedence rules.
Models
Codex supports the following models:
- GPT-5.3 Codex - Latest Codex model optimized for coding tasks. Requires a connected ChatGPT Pro or Plus plan.
- GPT-5.3 Codex Spark - Lightweight variant of GPT-5.3 Codex, optimized for faster execution. Requires a connected ChatGPT Pro plan.
- GPT-5.2 - GPT model with advanced reasoning
- GPT-5.2 Codex - Specialized variant optimized for coding tasks
Each model supports configurable reasoning effort levels: medium, high, and xhigh. This means there are twelve model variants available in total.
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. Xhigh applies maximum reasoning effort, producing the best results for complex tasks but with higher cost and latency.
Learn more about OpenAI models in the OpenAI documentation.
Usage stats
If you've connected your ChatGPT Pro plan, Superconductor shows your rate limit utilization. See Usage stats for details.