[Integrations](https://spiral.ai/integrations) › [Cursor](https://spiral.ai/integrations/cursor) › [Claude Opus 4.8](https://spiral.ai/integrations/cursor/claude-opus-4-8)

# How to Use Claude Opus 4.8 in Cursor

Claude Opus 4.8 suits complex coding, document analysis, and tasks that require several steps. Compared with Claude Opus 4.7, Anthropic reports it is about four times less likely to leave flaws in its own code unflagged.

|  |  |
| --- | --- |
| Model | Claude Opus 4.8 |
| 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 4.8 in Cursor

- Use Claude Opus 4.8 with extra high reasoning effort to investigate the failing tests in this project. Trace the cause, make the smallest justified fix, and report which checks passed.
- Use Claude Opus 4.8 to review the current diff for bugs that could cause incorrect behavior or test failures. Include the affected location, evidence, severity, and confidence for every finding.
- Use Claude Opus 4.8 with extra high reasoning effort to inspect the authentication flow and plan a refactor. Preserve existing behavior, identify dependencies, and define acceptance checks before editing.
- Use Claude Opus 4.8 to compare this project's implementation with its written requirements. Apply every requirement to all relevant modules and report missing behavior with supporting code locations.
- Use Claude Opus 4.8 to turn the project's architecture notes into a technical decision memo. Compare the documented approaches, state unresolved questions, and keep the memo under 800 words.

## How to set up Claude Opus 4.8 in Cursor

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

### Use Spiral's MCP server

1. **Add the hosted server**: Use Add to Cursor on the console's Agents & MCP page, or add this to `.cursor/mcp.json` (one project) or `~/.cursor/mcp.json` (every project):

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

2. **Sign in**: Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.

### Use the Spiral skill

1. **Send Cursor 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 4.8**: 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-4.8",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Cursor finds Claude Opus 4.8 on Spiral, shows the price and runs it.

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

## Claude Opus 4.8 tools and prices

- [Claude Opus 4.8](https://spiral.ai/tools/anthropic/anthropic/claude-opus-4.8) (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 4.8 in Cursor?

Claude Opus 4.8 can help trace bugs across a project, review changes, and carry a migration through several steps. Give it concrete acceptance criteria and ask it to distinguish code changes from verified results.

### Investigate a difficult bug

Trace a failure across related functions, identify the cause, and propose a fix with a regression check.

### Review a code change

Look for incorrect behavior, missing error handling, and test failures. Request evidence, severity, and confidence for each finding.

### Plan a code migration

Compare existing behavior with the target requirements, map dependencies, and produce an ordered implementation and validation plan.

### Compare competing proposals

Evaluate supplied proposals against the same criteria and produce a decision table that exposes missing information.

### Extract records from text

Turn meeting notes or business correspondence into consistently formatted records with explicit rules for missing values.

### Build a research brief

Combine supplied source text into a focused brief that separates agreement, conflicting evidence, and unanswered questions.

### Draft a technical decision memo

Turn requirements, constraints, and proposed approaches into a memo covering tradeoffs and the evidence needed to choose.

### Summarize recurring operational issues

Analyze a supplied batch of incident summaries or support conversations and organize recurring problems for review.

## Overview

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

## Claude Opus 4.8 in other agents

- [Amp](https://spiral.ai/integrations/amp/claude-opus-4-8)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/claude-opus-4-8)
- [Claude](https://spiral.ai/integrations/claude-desktop/claude-opus-4-8)
- [Claude Code](https://spiral.ai/integrations/claude-code/claude-opus-4-8)
- [Cline](https://spiral.ai/integrations/cline/claude-opus-4-8)
- [Codex](https://spiral.ai/integrations/codex/claude-opus-4-8)
- [Devin](https://spiral.ai/integrations/devin/claude-opus-4-8)
- [dots](https://spiral.ai/integrations/dots/claude-opus-4-8)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/claude-opus-4-8)
- [Gemini](https://spiral.ai/integrations/gemini/claude-opus-4-8)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/claude-opus-4-8)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/claude-opus-4-8)
- [goose](https://spiral.ai/integrations/goose/claude-opus-4-8)
- [Grok](https://spiral.ai/integrations/grok/claude-opus-4-8)
- [Grok Build](https://spiral.ai/integrations/grok-build/claude-opus-4-8)
- [Hermes](https://spiral.ai/integrations/hermes/claude-opus-4-8)
- [Instinct](https://spiral.ai/integrations/instinct/claude-opus-4-8)
- [Manus](https://spiral.ai/integrations/manus/claude-opus-4-8)
- [Muse](https://spiral.ai/integrations/muse/claude-opus-4-8)
- [Muse Code](https://spiral.ai/integrations/muse-code/claude-opus-4-8)
- [n8n](https://spiral.ai/integrations/n8n/claude-opus-4-8)
- [Notion](https://spiral.ai/integrations/notion/claude-opus-4-8)
- [OpenClaw](https://spiral.ai/integrations/openclaw/claude-opus-4-8)
- [opencode](https://spiral.ai/integrations/opencode/claude-opus-4-8)
- [Perplexity](https://spiral.ai/integrations/perplexity/claude-opus-4-8)
- [Raycast](https://spiral.ai/integrations/raycast/claude-opus-4-8)
- [VS Code](https://spiral.ai/integrations/vscode/claude-opus-4-8)
- [Windsurf](https://spiral.ai/integrations/windsurf/claude-opus-4-8)
- [Zapier](https://spiral.ai/integrations/zapier/claude-opus-4-8)

## More Cursor guides

- [Claude Opus 4.7](https://spiral.ai/integrations/cursor/claude-opus-4-7)
- [Claude Opus 5](https://spiral.ai/integrations/cursor/claude-opus-5)
- [Claude Opus 4.6](https://spiral.ai/integrations/cursor/claude-opus-4-6)
- [Claude Opus 5.5](https://spiral.ai/integrations/cursor/claude-opus-5-5)
- [Claude Opus 4.5](https://spiral.ai/integrations/cursor/claude-opus-4-5)
- [Claude Opus Latest](https://spiral.ai/integrations/cursor/claude-opus-latest)

## Questions about Claude Opus 4.8 in Cursor

**Can Cursor use Claude Opus 4.8?**

Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run Claude Opus 4.8 like any built-in tool.

**How much does Claude Opus 4.8 cost in Cursor?**

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 Cursor plan is separate.

**Do I need an Anthropic account to use Claude Opus 4.8 in Cursor?**

No. Spiral runs Claude Opus 4.8 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 4.8 in Cursor?**

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

**Does Cursor wait while Claude Opus 4.8 runs?**

Claude Opus 4.8 runs in the background. Cursor starts the run, checks on it and gives you the text, json when it's ready.

**What is Claude Opus 4.8 good at?**

Use it for complex coding, bug investigation, document analysis, and work that takes several steps. It also suits extracting consistent records from text when you define the expected output precisely.

**How much text can Claude Opus 4.8 handle?**

Its context window holds up to 1 million tokens, including conversation history and generated output, with a standard output limit of 128,000 tokens. Keep the supplied material relevant because accuracy and recall can decline as context grows.

**Which reasoning effort should I use?**

Anthropic recommends extra high effort for coding and tasks involving multiple agent actions, and high effort for other demanding analysis. Try lower effort on narrowly defined tasks and check whether the results still meet your requirements.

**How should I prompt Claude Opus 4.8?**

State the task, scope, constraints, and exact output you want. Say whether each instruction applies to every record or section because Claude Opus 4.8 follows wording literally.

**Why might Claude Opus 4.8 omit bugs during a code review?**

Instructions such as “only report important issues” can make it filter out bugs it considers below that threshold. Define what counts as a reportable bug, or request findings with severity and confidence so you can assess them afterward.

