Available on the Core plan and higher. Codex Agent runs on Ona Cloud and supported customer-managed runners. Contact sales to learn more.
How Codex Agent works
Codex Agent can read your repository, use configured tools, run commands, and open pull requests while following your organization’s policies. On Ona Cloud, Codex Agent uses the model access available to your organization. Core users can connect their ChatGPT account so Codex model requests use their ChatGPT plan instead. On a customer-managed runner, Codex Agent uses OpenAI model access provided by Ona Intelligence or an OpenAI-compatible LLM integration configured for that runner. See Model access for the available options.Prerequisites
- Your organization is on a Core or Enterprise plan.
- Codex Agent is enabled for your organization.
- Customer-managed runners require OpenAI model access through Ona Intelligence or an OpenAI-compatible LLM integration.
Start Codex Agent
- Start an environment.
- Open the conversation menu.
- Choose Codex.
- Describe the task you want Codex Agent to work on.
Choose a model
Choose GPT-6 Sol or GPT-6 Luna from the Codex model menu for conversations and automations. Available models depend on your model provider, organization policy, and the agent version installed in the environment. Existing conversations and automations retain their saved model settings. Both models offer Low, Medium, High, and Extra high reasoning. Medium reasoning and Standard speed remain the defaults. Fast is available when your provider and organization policy allow it.Organization controls
Administrators can control Codex Agent behavior for the organization.Model availability
In Organization Settings > Agents, administrators can allow or disable GPT-6 Sol and GPT-6 Luna independently, limit reasoning effort, and control Fast mode.Goal mode
Goal mode lets members set Codex goals that keep running until achieved. It is enabled by default. To change it, go to Organization Settings > Agents and toggle Goal mode in the Codex settings. When disabled, members can still run Codex Agent, but requests that ask it to run in goal mode are rejected.Usage and billing
Compute and model usage follow your organization’s plan and model-access configuration:- On Core, the environment consumes OCUs while Codex Agent runs. If you connect your ChatGPT account, OpenAI manages usage and limits for Codex model requests, and Ona does not charge OCUs for those model requests.
- On Enterprise, model usage follows the Ona Intelligence or BYOK configuration for your runner.
Related setup
- Connect Codex to ChatGPT: use your ChatGPT plan for Codex model requests
- Model access: configure model access for customer-managed runners
- AGENTS.md: add project context for agents
- MCP servers: extend agent capabilities with external tools