[Integrations](https://spiral.ai/integrations) › [Windsurf](https://spiral.ai/integrations/windsurf) › [GPT-5.3-Codex](https://spiral.ai/integrations/windsurf/gpt-5-3-codex)

# How to Use GPT-5.3-Codex in Windsurf

GPT-5.3-Codex writes, reviews, and debugs code. Its scope also covers product requirements, tests, and monitoring, making it useful for work that continues beyond the code change.

|  |  |
| --- | --- |
| Model | GPT-5.3-Codex |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5.3-Codex in Windsurf

- Use GPT-5.3-Codex with medium reasoning effort to investigate this project's failing tests. Reproduce the first failure, fix its cause, and run the relevant checks. Report the change and any remaining failures.
- Use GPT-5.3-Codex with high reasoning effort to review the current diff. Focus on bugs and backward compatibility. For each finding, identify the location, a failure scenario, and the test that would catch it.
- Use GPT-5.3-Codex to add pagination to this project's results screen. Follow existing components, preserve filtering behavior, and cover empty results and the final page. Run the relevant tests.
- Use GPT-5.3-Codex to trace how this project's settings are saved. Fix the case where the interface reports success but a refresh loses the change. Add a regression test and verify persistence.
- Use GPT-5.3-Codex to compare the feature requirements with the implementation and tests in this project. Identify missing acceptance criteria, implement the clearly specified behavior, and report unresolved product decisions.

## How to set up GPT-5.3-Codex in Windsurf

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

### Use Spiral's MCP server

1. **Add the server**: Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: `~/.config/devin/mcp_config.json` on macOS and Linux, `%APPDATA%\devin\mcp_config.json` on Windows. Add this:

```json
{
  "mcpServers": {
    "spiral": {
      "url": "https://api.spiral.ai/mcp"
    }
  }
}
```

2. **Sign in**: Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.

```bash
devin mcp login spiral
```

3. **Check it**: Spiral is listed under This computer in Customize › MCPs. From the terminal:

```bash
devin mcp list
```

### Use the Spiral skill

1. **Send Windsurf 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-5.3-Codex**: 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-5.3-codex",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Windsurf finds GPT-5.3-Codex on Spiral, shows the price and runs it.

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

## GPT-5.3-Codex tools and prices

- [GPT-5.3-Codex](https://spiral.ai/tools/openai/openai/gpt-5.3-codex) (OpenAI): Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 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 | low, medium, high, xhigh | — | How much the model reasons. |

## What can you do with GPT-5.3-Codex in Windsurf?

Turn a reproducible bug or feature request into code, tests, and a review of the result with GPT-5.3-Codex. Point the agent to relevant project files and define the behavior it should verify.

### Reproduce and repair a bug

Give GPT-5.3-Codex the failure, expected behavior, and relevant code. Request a focused fix and a regression test.

### Review a proposed change

Ask GPT-5.3-Codex to inspect a diff for behavior changes and explain each finding with a concrete failure scenario.

### Design regression tests

Have GPT-5.3-Codex turn a bug report or requirement into tests with explicit inputs and expected results.

### Implement a web feature

Ask GPT-5.3-Codex to write a feature with defined loading, empty, success, and error behavior.

### Draft product requirements

Use GPT-5.3-Codex to turn a feature brief into requirements, acceptance criteria, and unresolved product decisions.

### Triage monitoring alerts

Have GPT-5.3-Codex compare alert details, logs, and recent changes, then propose checks that distinguish possible causes.

### Edit product copy

Ask GPT-5.3-Codex to revise interface messages against the specified behavior and flag claims the requirements do not support.

## Overview

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

## GPT-5.3-Codex in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-5-3-codex)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-5-3-codex)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-5-3-codex)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-5-3-codex)
- [Cline](https://spiral.ai/integrations/cline/gpt-5-3-codex)
- [Codex](https://spiral.ai/integrations/codex/gpt-5-3-codex)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-5-3-codex)
- [Devin](https://spiral.ai/integrations/devin/gpt-5-3-codex)
- [dots](https://spiral.ai/integrations/dots/gpt-5-3-codex)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-5-3-codex)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-5-3-codex)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-5-3-codex)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-5-3-codex)
- [goose](https://spiral.ai/integrations/goose/gpt-5-3-codex)
- [Grok](https://spiral.ai/integrations/grok/gpt-5-3-codex)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-5-3-codex)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-5-3-codex)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-5-3-codex)
- [Manus](https://spiral.ai/integrations/manus/gpt-5-3-codex)
- [Muse](https://spiral.ai/integrations/muse/gpt-5-3-codex)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-5-3-codex)
- [n8n](https://spiral.ai/integrations/n8n/gpt-5-3-codex)
- [Notion](https://spiral.ai/integrations/notion/gpt-5-3-codex)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-5-3-codex)
- [opencode](https://spiral.ai/integrations/opencode/gpt-5-3-codex)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-5-3-codex)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-5-3-codex)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-5-3-codex)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-5-3-codex)

## More Windsurf guides

- [GPT-5.2 Pro](https://spiral.ai/integrations/windsurf/gpt-5-2-pro)
- [GPT-5.4](https://spiral.ai/integrations/windsurf/gpt-5-4)
- [GPT-5.2](https://spiral.ai/integrations/windsurf/gpt-5-2)
- [GPT-5.4 Nano](https://spiral.ai/integrations/windsurf/gpt-5-4-nano)
- [GPT-5.1](https://spiral.ai/integrations/windsurf/gpt-5-1)
- [GPT-5.4 Pro](https://spiral.ai/integrations/windsurf/gpt-5-4-pro)

## Questions about GPT-5.3-Codex in Windsurf

**Can Windsurf use GPT-5.3-Codex?**

Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run GPT-5.3-Codex like any built-in tool.

**How much does GPT-5.3-Codex cost in Windsurf?**

Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Windsurf plan is separate.

**Do I need an OpenAI account to use GPT-5.3-Codex in Windsurf?**

No. Spiral runs GPT-5.3-Codex 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-5.3-Codex in Windsurf?**

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

**Does Windsurf wait while GPT-5.3-Codex runs?**

GPT-5.3-Codex runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-5.3-Codex useful for?**

Use it to write, review, or debug code and to handle related work such as test design, product requirements, and monitoring analysis. Give it a concrete task and a clear definition of done.

**How much text can GPT-5.3-Codex handle?**

OpenAI lists a 400,000-token context window, a maximum of 272,000 input tokens, and up to 128,000 output tokens. Treat these as ceilings when deciding how much material to include.

**Which reasoning effort should I use?**

Start with medium for interactive coding. Try high or extra high for difficult debugging or other tasks where the first attempt needs deeper reasoning.

**What should I include in a coding prompt?**

Describe the expected behavior, provide the relevant code or reproduction steps, and state the constraints. Explain how to verify success, such as a failing test that should pass after the fix.

**Is GPT-5.3-Codex intended for casual conversation?**

OpenAI says it is not intended for conversational use. In a chat app, give it focused technical tasks such as reviewing pasted code, explaining a failure, or drafting test cases.

