# Codex with the Automation Platform

> Run Codex with the Automation Platform for codebase migrations, release coordination, batch test generation, and backend or DevOps automation.

- 网址：https://funcoding.ai/agents/warp/platform/harnesses/codex/
- 来源：Warp 官方文档原文（英文），MIT 许可，同步于 2026-10-11
- 官方原文：https://docs.warp.dev/platform/harnesses/codex/

---
Codex is OpenAI's coding agent. Running it with the Automation Platform puts Codex inside a Warp-managed environment and connects it to the rest of the Automation Platform — including triggers, environments, secrets, observability, and governance — while still behaving like the Codex CLI your team already uses.

<div class="callout callout-note">

This page covers Codex as a **cloud** harness, dispatched and orchestrated by the Automation Platform. To run Codex locally in your Warp terminal, see [Codex CLI in Warp](https://funcoding.ai/agents/warp/agents/cli-agents/codex/) instead.

</div>

## Key features

* **Cloud orchestration** - Launch Codex from any Automation Platform trigger: the Warp app, the Oz web app, the Oz CLI, the REST API, [schedules](https://funcoding.ai/agents/warp/platform/triggers/scheduled-agents/), [Slack](https://funcoding.ai/agents/warp/platform/integrations/slack/) mentions, Linear issues, or GitHub Actions.
* **Codex model picker** - Choose the OpenAI model Codex uses, including the GPT-5 lineup and Codex-tuned variants, each available at a configurable reasoning level.
* **First-class subagent** - A Warp Agent parent can dispatch Codex subagents to handle high-volume or well-defined coding steps inside a larger [multi-agent orchestration](https://funcoding.ai/agents/warp/platform/orchestration/).

## Available models

The Codex harness exposes OpenAI's Codex-tuned and general coding models, each available at a configurable reasoning level (low, medium, high, or extra-high). Common choices include:

* `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` - The latest generation of Codex-tuned coding models.
* `gpt-5.5` - The prior generation's coding model, still supported.
* `gpt-5.4`, `gpt-5.4-mini` - Fallback options for accounts without access to the newer models; `gpt-5.4-mini` is faster and lower-cost for lighter coding tasks or subagents.
* `gpt-5.3-codex` - An older Codex-tuned model, still available as an alternative.

Codex has no `default` model that picks automatically; every option names a specific model and reasoning level. For the full list, including Codex-tuned and general models, open the model picker on the Oz web app's new-run pane. For details on each model, see [OpenAI's Codex model docs](https://developers.openai.com/codex/models).

## Credentials and billing

Codex calls OpenAI directly using credentials your team provides. The Automation Platform supports one credential type today, stored as a [Warp-managed secret](https://funcoding.ai/agents/warp/platform/secrets/):

* **OpenAI API key** - The Codex harness authenticates to OpenAI using this key for every run.

OpenAI bills your account directly for inference. Warp still meters [compute credits](https://funcoding.ai/agents/warp/support-and-community/plans-and-billing/credits/#compute-credits) for the run's sandbox and [platform credits](https://funcoding.ai/agents/warp/support-and-community/plans-and-billing/platform-credits/) for the orchestration layer.

For setup steps, see [Connecting Codex credentials](https://funcoding.ai/agents/warp/platform/harnesses/authentication/#connecting-codex-credentials).

## Starting a Codex run

* **Warp app** - In Cloud Mode, click the **Agent harness** dropdown above the input and choose **Codex**.
* **Oz web app** - On the new run or new schedule pane, choose **Codex** in the **Harness** field. A **Codex auth secret** field appears below it; pick the OpenAI secret your team has stored.
* **API and SDK** - Set the agent config `harness` to `codex` and the OpenAI secret name on the matching auth-secret field. See the [API reference](https://funcoding.ai/agents/warp/factories/api-and-sdk/).

## Related pages

* [Harnesses in the Automation Platform](https://funcoding.ai/agents/warp/platform/harnesses/) — choose between Warp Agent, Claude Code, and Codex.
* [Authentication](https://funcoding.ai/agents/warp/platform/harnesses/authentication/) — store OpenAI credentials as Warp-managed secrets.
* [Warp Agent with the Automation Platform](https://funcoding.ai/agents/warp/platform/harnesses/warp-agent/) — the Automation Platform's default harness, the only one that can orchestrate Codex subagents.
* [Multi-agent orchestration](https://funcoding.ai/agents/warp/platform/orchestration/) — coordinate a Warp Agent parent with Codex children across local and cloud runs.
* [Managing cloud agents](https://funcoding.ai/agents/warp/platform/managing-cloud-agents/) — inspect Codex cloud runs in the Agent Management Panel and the Runs page.
* [Claude Code with the Automation Platform](https://funcoding.ai/agents/warp/platform/harnesses/claude-code/) — Claude Code as a cloud harness.
* [Codex CLI in Warp](https://funcoding.ai/agents/warp/agents/cli-agents/codex/) — Codex in your local Warp terminal.
* [Factory agents](https://funcoding.ai/agents/warp/factories/factory-agents/#configuring-a-third-party-harness) — configure Codex as a factory agent's harness.