[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Claude Opus 4.5](https://spiral.ai/integrations/openclaw/claude-opus-4-5)

# How to Use Claude Opus 4.5 in OpenClaw

Claude Opus 4.5 suits difficult software engineering and detailed research. Its 200,000-token context window and maximum 64,000-token output give it room for large code reviews and substantial reports.

|  |  |
| --- | --- |
| Model | Claude Opus 4.5 |
| 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 4.5 in OpenClaw

- Use Claude Opus 4.5 each morning to compare newly supplied research with the previous brief. Report changed conclusions, quote the evidence behind each change, and keep the update under 500 words.
- Use Claude Opus 4.5 each week to compare the supplied business tables with last week's results. Explain the largest discrepancies, show supporting calculations, and separate confirmed causes from hypotheses.
- Use Claude Opus 4.5 every Friday to turn the supplied research updates into a six-slide briefing outline. Include one evidence-backed headline per slide and a final slide of unresolved questions.
- Use Claude Opus 4.5 each day to compare newly supplied vendor announcements with our requirements. Quote relevant passages and report only changes that could affect the decision.
- Use Claude Opus 4.5 each week to summarize the supplied research digest in Spanish for readers in Mexico. Preserve figures and source references, and identify passages whose meaning is ambiguous.

## How to set up Claude Opus 4.5 in OpenClaw

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

### Use the Spiral skill

1. **Send OpenClaw 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 Spiral's MCP server

1. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### 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 4.5**: 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-4.5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Claude Opus 4.5 on Spiral, shows the price and runs it.

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

## Claude Opus 4.5 tools and prices

- [Claude Opus 4.5](https://spiral.ai/tools/anthropic/anthropic/claude-opus-4.5) (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 |  | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 64000 | — | 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). |
| temperature | 0 to 1 | — |  |
| tool_choice |  | — |  |

## What can you do with Claude Opus 4.5 in OpenClaw?

Claude Opus 4.5 can produce recurring research comparisons and explanations of business results. Give each run current evidence and a previous baseline so its report can focus on meaningful changes.

### Investigate bugs across components

Use Claude Opus 4.5 to trace a failure through related code, explain the cause, and propose a focused fix with a regression check.

### Review substantial code changes

Ask Claude Opus 4.5 to examine a change for correctness, identify affected behavior, and rank findings by impact.

### Plan a code migration

Have Claude Opus 4.5 map dependencies, divide a migration into testable steps, and define checks for preserving existing behavior.

### Reconcile conflicting research

Give Claude Opus 4.5 source material and ask for an evidence table that separates agreement, contradictions, and unanswered questions.

### Explain spreadsheet discrepancies

Ask Claude Opus 4.5 to examine supplied tables and formulas, trace inconsistent totals, and explain which assumptions need checking.

### Draft an evidence-based presentation

Use Claude Opus 4.5 to turn research and business results into slide headlines, supporting evidence, and speaker notes.

### Adapt research for another language

Ask Claude Opus 4.5 to summarize supplied findings in a named language while preserving technical terms, numbers, and source references.

## Overview

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

## Claude Opus 4.5 in other agents

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

## More OpenClaw guides

- [Claude Haiku Latest](https://spiral.ai/integrations/openclaw/claude-haiku-latest)
- [Claude Opus 4.6](https://spiral.ai/integrations/openclaw/claude-opus-4-6)
- [Claude Haiku 5.5](https://spiral.ai/integrations/openclaw/claude-haiku-5-5)
- [Claude Opus 4.7](https://spiral.ai/integrations/openclaw/claude-opus-4-7)
- [Claude Haiku 4.5](https://spiral.ai/integrations/openclaw/claude-haiku-4-5)
- [Claude Opus 4.8](https://spiral.ai/integrations/openclaw/claude-opus-4-8)

## Questions about Claude Opus 4.5 in OpenClaw

**Can OpenClaw use Claude Opus 4.5?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Claude Opus 4.5 like any built-in tool.

**How much does Claude Opus 4.5 cost in OpenClaw?**

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 OpenClaw plan is separate.

**Do I need an Anthropic account to use Claude Opus 4.5 in OpenClaw?**

No. Spiral runs Claude Opus 4.5 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 4.5 in OpenClaw?**

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

**Does OpenClaw wait while Claude Opus 4.5 runs?**

Claude Opus 4.5 runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Claude Opus 4.5 good at?**

Difficult software engineering, deep research, and analysis involving spreadsheets or presentations are documented strengths. Try it for a bug that crosses several components or a report that must reconcile conflicting evidence.

**How much context and output can Claude Opus 4.5 handle?**

It has a 200,000-token context window and can generate up to 64,000 output tokens. Treat these as token limits rather than fixed page counts.

**Does Claude Opus 4.5 generate images or video?**

Its output is text. Use it to write code, reports, presentation copy, or production briefs.

**What limitations should I plan around?**

Anthropic documents a tendency to overengineer code, so specify the exact scope and ask for minimal changes. Its reliable knowledge cutoff is May 2025; supply current evidence for questions about later events.

**How should I prompt Claude Opus 4.5 for document analysis?**

Ask it to extract relevant passages before drawing conclusions. Request a source reference beside each conclusion so you can check the reasoning against the supplied material.

