[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Claude Opus 5](https://spiral.ai/integrations/chatgpt/claude-opus-5)

# How to Use Claude Opus 5 in ChatGPT

Claude Opus 5 suits difficult debugging, large refactors, and tasks that span many steps. Compared with Claude Opus 4.8, its coding improvements are most useful for complex changes across multiple files.

|  |  |
| --- | --- |
| Model | Claude Opus 5 |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Claude Opus 5 in ChatGPT

- Use Claude Opus 5 to compare the reports above. Identify three disagreements, cite supporting passages, and keep the answer under 300 words.
- Use Claude Opus 5 to explain the formulas needed to connect monthly revenue, expenses, and cash balance across three spreadsheet sheets.
- Use Claude Opus 5 to analyze the account-health figures above. Rank the five highest risks and explain each using the supplied evidence.
- Use Claude Opus 5 to diagnose the bug from the code and error trace above. Explain the cause and propose a focused correction.
- Use Claude Opus 5 with high reasoning effort to compare these architecture proposals. Recommend one in 200 words and state the deciding tradeoff.

## How to set up Claude Opus 5 in ChatGPT

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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 Claude Opus 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": "anthropic",
    "model": "anthropic/claude-opus-5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Claude Opus 5 on Spiral, shows the price and runs it.

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

## Claude Opus 5 tools and prices

- [Claude Opus 5](https://spiral.ai/tools/anthropic/anthropic/claude-opus-5) (Anthropic): Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 128000 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with Claude Opus 5 in ChatGPT?

Claude Opus 5 can turn extensive source material into comparisons and practical recommendations. Set a clear question and answer length to keep the discussion useful.

### Fix bugs that survive an initial patch

Use Claude Opus 5 to trace a failure to its cause and address related edge cases.

### Refactor code across multiple files

Use Claude Opus 5 for coordinated changes across modules while preserving the behavior you specify.

### Implement a complete feature

Give Claude Opus 5 the behavior, constraints, and acceptance criteria for a feature spanning several parts of an application.

### Compare lengthy reports

Use Claude Opus 5 to compare supplied reports, surface disagreements, and link conclusions to supporting passages.

### Develop spreadsheet formulas

Ask Claude Opus 5 to design formulas across related sheets and explain their assumptions.

### Review account health

Use Claude Opus 5 to turn account-health data into a prioritized risk summary and suggested next actions.

## Overview

- [Anthropic Claude](https://spiral.ai/providers/anthropic)
- [All ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## Claude Opus 5 in other agents

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

## More ChatGPT guides

- [Claude Opus 4.8](https://spiral.ai/integrations/chatgpt/claude-opus-4-8)
- [Claude Opus 5.5](https://spiral.ai/integrations/chatgpt/claude-opus-5-5)
- [Claude Opus 4.7](https://spiral.ai/integrations/chatgpt/claude-opus-4-7)
- [Claude Opus Latest](https://spiral.ai/integrations/chatgpt/claude-opus-latest)
- [Claude Opus 4.6](https://spiral.ai/integrations/chatgpt/claude-opus-4-6)
- [Claude Sonnet 4.6](https://spiral.ai/integrations/chatgpt/claude-sonnet-4-6)

## Questions about Claude Opus 5 in ChatGPT

**Can ChatGPT use Claude Opus 5?**

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

**How much does Claude Opus 5 cost in ChatGPT?**

Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.

**Do I need an Anthropic account to use Claude Opus 5 in ChatGPT?**

No. Spiral runs Claude Opus 5 on its own Anthropic account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Claude Opus 5 in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while Claude Opus 5 runs?**

Claude Opus 5 runs in the background. ChatGPT starts the run, checks on it and gives you the text, json when it's ready.

**How much text can Claude Opus 5 handle?**

Its context window holds up to 1 million tokens, and its standard maximum output is 128,000 tokens. These are token limits, so avoid treating them as fixed word or page counts.

**Which reasoning effort should I use?**

Start with high. Test xhigh on difficult coding or extended agent tasks, and compare low or medium on simpler work where your evaluations show acceptable results.

**How do I get shorter answers?**

Give Claude Opus 5 a concrete length target, such as 150 words or five bullets. Changing reasoning effort does not reliably shorten the visible answer.

**How do I keep Claude Opus 5 focused on a small task?**

State the exact deliverable and the boundary of the work. For example, ask it to fix one parsing bug while preserving the public interface.

**Can Claude Opus 5 give incorrect answers?**

Yes. For document analysis, ask for supporting passages and let it say when the supplied material does not establish an answer.

