[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Claude Opus 4.6](https://spiral.ai/integrations/openclaw/claude-opus-4-6)

# How to Use Claude Opus 4.6 in OpenClaw

Claude Opus 4.6 suits complex coding tasks, code review, and research across long documents. Compared with Claude Opus 4.5, it improves planning, debugging, and sustained work in large codebases.

|  |  |
| --- | --- |
| Model | Claude Opus 4.6 |
| 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 4.6 in OpenClaw

- Each morning, use Claude Opus 4.6 to summarize the source updates supplied for that run. Report only developments absent from the previous brief, cite their sources, and say when there is nothing new.
- Each week, use Claude Opus 4.6 with high reasoning effort to compare the supplied research updates with the previous conclusions. Identify which conclusions still hold and which need revision, with supporting quotes.
- At each scheduled run, use Claude Opus 4.6 to compare the supplied policy text with the earlier text. Report changes to obligations and deadlines, quoting the old and new wording.
- Every Friday, use Claude Opus 4.6 to analyze the supplied financial figures and management commentary. Explain material changes, distinguish stated causes from hypotheses, and list missing evidence.
- Each evening, use Claude Opus 4.6 with medium reasoning effort to turn the supplied project updates into a brief under 250 words. Include decisions, blockers, and explicitly assigned actions; leave unstated owners and dates unknown.

## How to set up Claude Opus 4.6 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 4.6**: 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-4.6",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Claude Opus 4.6 on Spiral, shows the price and runs it.

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

## Claude Opus 4.6 tools and prices

- [Claude Opus 4.6](https://spiral.ai/tools/anthropic/anthropic/claude-opus-4.6) (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 | — | Taken only at reasoning effort "none", this model's default. |
| 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). |
| temperature | 0 to 1 | — | Taken only at reasoning effort "none", this model's default. |

## What can you do with Claude Opus 4.6 in OpenClaw?

Claude Opus 4.6 can produce recurring briefs from supplied updates and compare new evidence with earlier findings. Define what counts as a meaningful change and require a source for each reported development.

### Debug a failure across several modules

Have Claude Opus 4.6 trace a failing behavior through the relevant code, propose a focused fix, and explain which test would catch a recurrence.

### Review a substantial code change

Ask Claude Opus 4.6 to check a patch for behavioral regressions, missed edge cases, and assumptions that conflict with surrounding code.

### Explain an unfamiliar codebase

Use Claude Opus 4.6 to map a request path, identify the components involved, and explain where a proposed change belongs.

### Compare lengthy proposals

Give Claude Opus 4.6 the proposal text and evaluation criteria. Request an evidence table of commitments, gaps, and conflicting claims.

### Prepare a research brief

Ask Claude Opus 4.6 to synthesize supplied sources into findings, disagreements, and unanswered questions, with evidence for each conclusion.

### Explain financial performance

Provide Claude Opus 4.6 with reported figures and commentary. Request a variance narrative that separates reported causes from hypotheses and missing evidence.

## Overview

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

## Claude Opus 4.6 in other agents

- [Amp](https://spiral.ai/integrations/amp/claude-opus-4-6)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/claude-opus-4-6)
- [Claude](https://spiral.ai/integrations/claude-desktop/claude-opus-4-6)
- [Claude Code](https://spiral.ai/integrations/claude-code/claude-opus-4-6)
- [Cline](https://spiral.ai/integrations/cline/claude-opus-4-6)
- [Codex](https://spiral.ai/integrations/codex/claude-opus-4-6)
- [Cursor](https://spiral.ai/integrations/cursor/claude-opus-4-6)
- [Devin](https://spiral.ai/integrations/devin/claude-opus-4-6)
- [dots](https://spiral.ai/integrations/dots/claude-opus-4-6)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/claude-opus-4-6)
- [Gemini](https://spiral.ai/integrations/gemini/claude-opus-4-6)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/claude-opus-4-6)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/claude-opus-4-6)
- [goose](https://spiral.ai/integrations/goose/claude-opus-4-6)
- [Grok](https://spiral.ai/integrations/grok/claude-opus-4-6)
- [Grok Build](https://spiral.ai/integrations/grok-build/claude-opus-4-6)
- [Hermes](https://spiral.ai/integrations/hermes/claude-opus-4-6)
- [Instinct](https://spiral.ai/integrations/instinct/claude-opus-4-6)
- [Manus](https://spiral.ai/integrations/manus/claude-opus-4-6)
- [Muse](https://spiral.ai/integrations/muse/claude-opus-4-6)
- [Muse Code](https://spiral.ai/integrations/muse-code/claude-opus-4-6)
- [n8n](https://spiral.ai/integrations/n8n/claude-opus-4-6)
- [Notion](https://spiral.ai/integrations/notion/claude-opus-4-6)
- [opencode](https://spiral.ai/integrations/opencode/claude-opus-4-6)
- [Perplexity](https://spiral.ai/integrations/perplexity/claude-opus-4-6)
- [Raycast](https://spiral.ai/integrations/raycast/claude-opus-4-6)
- [VS Code](https://spiral.ai/integrations/vscode/claude-opus-4-6)
- [Windsurf](https://spiral.ai/integrations/windsurf/claude-opus-4-6)
- [Zapier](https://spiral.ai/integrations/zapier/claude-opus-4-6)

## More OpenClaw guides

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

## Questions about Claude Opus 4.6 in OpenClaw

**Can OpenClaw use Claude Opus 4.6?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Claude Opus 4.6 like any built-in tool.

**How much does Claude Opus 4.6 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 4.6 in OpenClaw?**

No. Spiral runs Claude Opus 4.6 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 4.6 in OpenClaw?**

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

**Does OpenClaw wait while Claude Opus 4.6 runs?**

Claude Opus 4.6 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 4.6 best used for?**

Use it for debugging, code review, and research that draws on substantial source material. It also suits document work and financial analysis where several pieces of evidence need to be considered together.

**How much text can Claude Opus 4.6 handle?**

Anthropic lists a 1 million token context window and a standard maximum output of 128,000 tokens. Those are capacity limits, so specify the answer length you actually need.

**What should I watch for when using Claude Opus 4.6?**

For coding, it can expand a small task into extra files or unnecessary abstractions. State the change boundary explicitly, such as fixing the failing behavior without restructuring unrelated code.

**How should I prompt Claude Opus 4.6 with long documents?**

Put the source material first and the question afterward. Define the deliverable, then ask for supporting quotes before conclusions so you can check the evidence.

**Which reasoning setting should I test first?**

Compare medium and high effort on representative tasks, checking correctness and completeness. Effort changes how much work Claude puts into the response, including tool calls and active thinking.

