[Integrations](https://spiral.ai/integrations) › [Amp](https://spiral.ai/integrations/amp) › [Muse Wonder](https://spiral.ai/integrations/amp/muse-wonder)

# How to Use Muse Wonder in Amp

Muse Wonder is built for multi-file code changes and tasks that require planning, testing, and revision. Maximum reasoning gives it more thinking time but does not turn it into Muse Wonder Full.

|  |  |
| --- | --- |
| Model | Muse Wonder |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.106678 per run at the default inputs. $5.20 per 1M input tokens, $26.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Muse Wonder in Amp

- Use Muse Wonder with high reasoning to trace the authentication flow in this repository. Identify inconsistent permission checks, fix them, and run the relevant tests.
- Use Muse Wonder with maximum reasoning to investigate duplicate queue processing after a restart. Reproduce the failure, compare likely causes, and verify the smallest fix.
- Use Muse Wonder with high reasoning to refactor duplicated validation across this project. Preserve behavior and verify each affected entry point.
- Use Muse Wonder with maximum reasoning to plan this repository's database migration. Identify dependencies, rollback conditions, and tests before making changes.
- Use Muse Wonder with high reasoning to review the current diff against the project's requirements. Investigate failures and report which acceptance criteria remain unverified.

## How to set up Muse Wonder in Amp

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

### Use Spiral's MCP server

1. **Add the server**: No header and no client ID or secret: Amp registers itself with Spiral.

```bash
amp mcp add spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `amp`. Amp opens Spiral's sign-in page in your browser: sign in, pick the organization and click Authorize. No API key.

3. **Check it**

```bash
amp mcp doctor
```

### Use the Spiral skill

1. **Send Amp 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 Muse Wonder**: 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": "openrouter",
    "model": "meta/muse-wonder",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Amp finds Muse Wonder on Spiral, shows the price and runs it.

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

## Muse Wonder tools and prices

- [Meta: Muse Wonder](https://spiral.ai/tools/openrouter/meta/muse-wonder) (OpenRouter): Up to $0.106678 per run at the default inputs. $5.20 per 1M input tokens, $26.00 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 943718 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Muse Wonder in Amp?

Muse Wonder can carry a repository change through investigation, edits, and verification across multiple files. Give it acceptance criteria and ask it to use test results to guide revisions.

### Refactor code across a repository

Use Muse Wonder to trace dependencies, change related modules, and verify that the revised code passes relevant tests.

### Investigate a recurring bug

Have Muse Wonder compare hypotheses, reproduce the failure, and revise its diagnosis as test results arrive.

### Plan a large code migration

Ask Muse Wonder to identify affected components, order the changes, and define validation and rollback criteria.

### Turn a long brief into an execution plan

Give Muse Wonder the requirements and constraints, then request milestones, dependencies, and explicit completion checks.

### Replan work after a blocker

Supply the current goal, completed work, failed attempts, and new constraints. Ask Muse Wonder for the next feasible approach.

### Review a proposed technical change

Have Muse Wonder examine a proposal alongside relevant code and test results, then identify unresolved assumptions and verification work.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Amp guides](https://spiral.ai/integrations/amp)

## Muse Wonder in other agents

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

## More Amp guides

- [Muse Spark Open](https://spiral.ai/integrations/amp/muse-spark-open)
- [MythoMax 13B](https://spiral.ai/integrations/amp/mythomax-13b)
- [Muse Spark 1.3 Contributor](https://spiral.ai/integrations/amp/muse-spark-1-3-contributor)
- [Nemotron 3 Nano 30B A3B](https://spiral.ai/integrations/amp/nemotron-3-nano-30b-a3b)
- [Muse Spark 1.3](https://spiral.ai/integrations/amp/muse-spark-1-3)
- [Nemotron 3 Super](https://spiral.ai/integrations/amp/nemotron-3-super)

## Questions about Muse Wonder in Amp

**Can Amp use Muse Wonder?**

Yes. Add Spiral to Amp as an MCP server, and Amp can find and run Muse Wonder like any built-in tool.

**How much does Muse Wonder cost in Amp?**

Up to $0.106678 per run at the default inputs. $5.20 per 1M input tokens, $26.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Amp plan is separate.

**Do I need an OpenRouter account to use Muse Wonder in Amp?**

No. Spiral runs Muse Wonder on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Muse Wonder in Amp?**

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

**Does Amp wait while Muse Wonder runs?**

Muse Wonder runs in the background. Amp starts the run, checks on it and gives you the text, json when it's ready.

**What is Muse Wonder best suited for?**

Use it for code changes spanning multiple files and tasks that need repeated planning, testing, and revision. Meta emphasizes sustained work that adapts when an approach fails.

**How much context can Muse Wonder handle?**

The documented context window is 1,048,576 tokens. Input and the requested output budget share that space, and internal reasoning consumes part of the output budget.

**Which reasoning setting should I use?**

Meta recommends high reasoning for agentic coding. Use lower effort for simpler requests, and reserve maximum reasoning for difficult debugging or migration planning.

**Does maximum reasoning give me Muse Wonder Full?**

No. It increases the reasoning effort of Muse Wonder; it does not select Muse Wonder Full.

**Where does Muse Wonder need extra checking?**

Precise visual and spatial reasoning, particularly 3D tasks, is a documented weakness. Verify measurements and spatial conclusions against the original material.

