[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [GPT-5.4 Pro](https://spiral.ai/integrations/codex/gpt-5-4-pro)

# How to Use GPT-5.4 Pro in Codex

GPT-5.4 Pro is for difficult analysis and coding problems that benefit from deeper reasoning. It uses more compute than GPT-5.4, with the same 1,050,000-token context window and 128,000-token output ceiling.

|  |  |
| --- | --- |
| Model | GPT-5.4 Pro |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.959829 per run at the default inputs. $39.00 per 1M input tokens, $234.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5.4 Pro in Codex

- Use GPT-5.4 Pro with high reasoning effort to review this project's database migration. Check prerequisites, compatibility, and rollback assumptions. Return a prioritized risk table with file references and a verification plan.
- Use GPT-5.4 Pro to compare two ways to remove the circular dependency in this project. Read the affected modules first. Recommend an approach using the existing architecture, explain tradeoffs, and list the checks needed after implementation.
- Ask GPT-5.4 Pro through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
- Get a second opinion from GPT-5.4 Pro on this function, then tell me what the call cost.
- Summarize these release notes with GPT-5.4 Pro in five bullet points.

## How to set up GPT-5.4 Pro in Codex

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GPT-5.4 Pro**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openai",
    "model": "openai/gpt-5.4-pro",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Codex finds GPT-5.4 Pro on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## GPT-5.4 Pro tools and prices

- [GPT-5.4 Pro](https://spiral.ai/tools/openai/openai/gpt-5.4-pro) (OpenAI): Up to $0.959829 per run at the default inputs. $39.00 per 1M input tokens, $234.00 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 16 to 128000 | — | The most output tokens to generate. |
| tool_choice |  | — |  |
| response_format |  | — |  |
| reasoning_effort | medium, high, xhigh | medium | How much the model reasons. |

## What can you do with GPT-5.4 Pro in Codex?

Turn project code and technical requirements into fixes, reviews, and implementation plans with GPT-5.4. Give the agent a concrete completion check and ask it to explain the evidence behind its changes.

### Find the cause of a bug

Trace a failure through code and logs, propose a focused fix, and define a check that reproduces the original problem.

### Review a migration plan

Compare the proposed changes with existing behavior. List dependencies, compatibility risks, and checks needed before rollout.

### Compare competing proposals

Turn supplied proposals into a decision table using explicit criteria. Separate documented commitments from assumptions and unanswered questions.

### Prepare a research brief

Combine supplied sources into a concise explanation with supporting passages, conflicting claims, and gaps that need further research.

### Check spreadsheet logic

Review supplied formulas and assumptions for inconsistent units, missing dependencies, and totals that need reconciliation.

### Draft a presentation

Turn a business brief into a slide outline with a clear recommendation, supporting evidence, and speaker notes.

### Explain a difficult technical decision

Compare engineering approaches against stated constraints. Describe tradeoffs, identify missing measurements, and recommend the next experiment.

### Produce a recurring operations brief

Summarize supplied updates into changes, blockers, and next actions. Keep each conclusion tied to the evidence available for that run.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All Codex guides](https://spiral.ai/integrations/codex)

## GPT-5.4 Pro in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-5-4-pro)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-5-4-pro)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-5-4-pro)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-5-4-pro)
- [Cline](https://spiral.ai/integrations/cline/gpt-5-4-pro)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-5-4-pro)
- [Devin](https://spiral.ai/integrations/devin/gpt-5-4-pro)
- [dots](https://spiral.ai/integrations/dots/gpt-5-4-pro)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-5-4-pro)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-5-4-pro)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-5-4-pro)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-5-4-pro)
- [goose](https://spiral.ai/integrations/goose/gpt-5-4-pro)
- [Grok](https://spiral.ai/integrations/grok/gpt-5-4-pro)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-5-4-pro)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-5-4-pro)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-5-4-pro)
- [Manus](https://spiral.ai/integrations/manus/gpt-5-4-pro)
- [Muse](https://spiral.ai/integrations/muse/gpt-5-4-pro)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-5-4-pro)
- [n8n](https://spiral.ai/integrations/n8n/gpt-5-4-pro)
- [Notion](https://spiral.ai/integrations/notion/gpt-5-4-pro)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-5-4-pro)
- [opencode](https://spiral.ai/integrations/opencode/gpt-5-4-pro)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-5-4-pro)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-5-4-pro)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-5-4-pro)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-5-4-pro)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-5-4-pro)

## More Codex guides

- [GPT-5.4 Nano](https://spiral.ai/integrations/codex/gpt-5-4-nano)
- [GPT-5.4 mini](https://spiral.ai/integrations/codex/gpt-5-4-mini)
- [GPT-5.4](https://spiral.ai/integrations/codex/gpt-5-4)
- [GPT-5.5](https://spiral.ai/integrations/codex/gpt-5-5)
- [GPT-5.3-Codex](https://spiral.ai/integrations/codex/gpt-5-3-codex)
- [GPT-5.5 Pro](https://spiral.ai/integrations/codex/gpt-5-5-pro)

## Questions about GPT-5.4 Pro in Codex

**Can Codex use GPT-5.4 Pro?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run GPT-5.4 Pro like any built-in tool.

**How much does GPT-5.4 Pro cost in Codex?**

Up to $0.959829 per run at the default inputs. $39.00 per 1M input tokens, $234.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need an OpenAI account to use GPT-5.4 Pro in Codex?**

No. Spiral runs GPT-5.4 Pro on its own OpenAI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GPT-5.4 Pro in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while GPT-5.4 Pro runs?**

GPT-5.4 Pro runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-5.4 good at?**

GPT-5.4 combines coding and reasoning with document, spreadsheet, and presentation work. Useful tasks include investigating bugs, comparing evidence, and turning business requirements into a draft deliverable.

**How much can GPT-5.4 read and write?**

GPT-5.4 and GPT-5.4 Pro each have a 1,050,000-token context window and a 128,000-token maximum output. Internal reasoning also uses the output budget, so that ceiling does not mean 128,000 tokens of visible text.

**Does GPT-5.4 know recent events?**

GPT-5.4 and GPT-5.4 Pro have an August 31, 2025 knowledge cutoff. Supply current source material when asking about later events or changes.

**What does reasoning effort change?**

It controls how much internal reasoning the model does before answering. Compare results on your actual task, and leave enough output space for both reasoning and the final answer.

**How should I prompt GPT-5.4?**

State the deliverable, the required sections, and a length limit. For example, ask for a recommendation, its supporting evidence, and unresolved questions in under 500 words.

