[Integrations](https://spiral.ai/integrations) › [goose](https://spiral.ai/integrations/goose) › [GPT-5](https://spiral.ai/integrations/goose/gpt-5)

# How to Use GPT-5 in goose

GPT-5 suits debugging, code edits, and tasks where you want to adjust reasoning effort. Its maximum output budget is 128,000 tokens, compared with GPT-5 Pro's 272,000.

|  |  |
| --- | --- |
| Model | GPT-5 |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.053306 per run at the default inputs. $1.625 per 1M input tokens, $0.1625 per 1M cached input tokens, $13.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5 in goose

- Use GPT-5 to investigate the failing tests in this project. Identify the cause, make the smallest correction that preserves the public interface, and report the checks you ran.
- Use GPT-5 to explain how authentication works in this repository. Trace one request through validation, session creation, and error handling, with references to the relevant files.
- Use GPT-5 with high reasoning effort to review the caching implementation in this repository. Find stale-data and invalidation risks, then propose a small patch with a regression test.
- Ask GPT-5 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 on this function, then tell me what the call cost.

## How to set up GPT-5 in goose

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

### Use Spiral's MCP server

1. **Add the extension**: In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:

2. **Sign in**: When goose first connects to Spiral, your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key. If the browser does not open, goose prints the link to open yourself.

### Use the Spiral skill

1. **Send goose 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**: 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",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: goose finds GPT-5 on Spiral, shows the price and runs it.

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

## GPT-5 tools and prices

- [GPT-5](https://spiral.ai/tools/openai/openai/gpt-5) (OpenAI): Up to $0.053306 per run at the default inputs. $1.625 per 1M input tokens, $0.1625 per 1M cached input tokens, $13.00 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| 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 |  | — |  |

## What can you do with GPT-5 in goose?

Turn a bug report into a focused code change, or get an explanation of unfamiliar project code. Give GPT-5 a clear scope and acceptance criteria so the result is easy to review.

### Debug a failing workflow

Provide the relevant code, error messages, and expected behavior. Ask for a likely cause, a focused correction, and a test that would catch the failure.

### Plan a code refactor

Ask for a refactor that preserves public behavior, identifies affected callers, and explains which checks should pass before accepting the change.

### Explain an unfamiliar codebase

Supply relevant modules and ask how a request moves through them. Request references to the functions that handle validation, state changes, and errors.

### Review a mathematical argument

Provide a proposed solution and ask for unsupported steps, missing assumptions, and a concise corrected argument.

### Draft a technical report

Turn supplied findings into a report for a defined audience. Require separate sections for observations, interpretation, and unresolved questions.

### Edit a decision memo

Ask for a clearer recommendation, explicit tradeoffs, and a list of claims that need supporting evidence. Set a word limit and preserve the supplied facts.

### Explain a scientific result

Provide the result, method, and stated assumptions. Ask for an explanation of the argument and questions that would help assess the conclusion.

## Overview

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

## GPT-5 in other agents

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

## More goose guides

- [GPT-4o mini (2024-07-18)](https://spiral.ai/integrations/goose/gpt-4o-mini-2024-07-18)
- [GPT-5 Mini](https://spiral.ai/integrations/goose/gpt-5-mini)
- [GPT-4o mini](https://spiral.ai/integrations/goose/gpt-4o-mini)
- [GPT-5 Nano](https://spiral.ai/integrations/goose/gpt-5-nano)
- [GPT-4o 2024-11-20](https://spiral.ai/integrations/goose/gpt-4o-2024-11-20)
- [GPT-5 Pro](https://spiral.ai/integrations/goose/gpt-5-pro)

## Questions about GPT-5 in goose

**Can goose use GPT-5?**

Yes. Add Spiral to goose as an MCP server, and goose can find and run GPT-5 like any built-in tool.

**How much does GPT-5 cost in goose?**

Up to $0.053306 per run at the default inputs. $1.625 per 1M input tokens, $0.1625 per 1M cached input tokens, $13.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your goose plan is separate.

**Do I need an OpenAI account to use GPT-5 in goose?**

No. Spiral runs GPT-5 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 in goose?**

About two minutes: add the extension, then sign in.

**Does goose wait while GPT-5 runs?**

GPT-5 runs in the background. goose starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-5 useful for?**

GPT-5 is useful for debugging, editing code, and explaining complex codebases. Practical writing tasks include drafting and editing reports, emails, and memos.

**How much context can GPT-5 handle?**

GPT-5 and GPT-5 Pro each have a 400,000-token context window. Treat that as a total context limit, rather than a promise that you can submit that much source text and still receive a full-length answer.

**Does GPT-5 know about recent events?**

GPT-5 and GPT-5 Pro have a September 30, 2024 knowledge cutoff. Supply dated source material when your question depends on newer events or changes.

**Can I ask GPT-5 for a short answer?**

Yes. Specify the length and structure directly, such as a 150-word explanation or a table followed by three recommendations.

**How should I prompt GPT-5?**

State the task, relevant evidence, constraints, and desired output clearly. Check that your instructions agree, especially when combining standing rules with a new request.

