[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [Amazon Nova Micro](https://spiral.ai/integrations/muse-code/amazon-nova-micro)

# How to Use Amazon Nova Micro in Muse Code

Amazon Nova Micro handles quick text summaries, translation, and classification. Unlike Amazon Nova Lite, it accepts text alone.

|  |  |
| --- | --- |
| Model | Amazon Nova Micro |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.000748 per run at the default inputs. $0.0455 per 1M input tokens, $0.182 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Amazon Nova Micro in Muse Code

- Use Amazon Nova Micro to summarize the current Git diff into release notes. Separate user-visible changes, bug fixes, and internal changes. Include only changes supported by the diff and keep the result under 250 words.
- Use Amazon Nova Micro to classify the issue descriptions in this project as bug, feature request, documentation, or question. Return one JSON object per issue with its ID, label, and a short supporting excerpt.
- Use Amazon Nova Micro to draft a small utility that trims leading and trailing whitespace from a string without changing internal whitespace. Follow the language and conventions used in this project, then run the relevant tests.
- Use Amazon Nova Micro to turn the README's installation and usage sections into six concise FAQ answers. Preserve commands exactly and mark any question the README does not answer.
- Use Amazon Nova Micro to summarize this project's failing test output. List each distinct failure, the named test, and the observed error. Keep diagnosis separate from facts and stay under 400 words.

## How to set up Amazon Nova Micro in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse Code 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 Amazon Nova Micro**: 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": "amazon/nova-micro-v1",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse Code finds Amazon Nova Micro on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## Amazon Nova Micro tools and prices

- [Amazon: Nova Micro 1.0](https://spiral.ai/tools/openrouter/amazon/nova-micro-v1) (OpenRouter): Up to $0.000748 per run at the default inputs. $0.0455 per 1M input tokens, $0.182 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 5120 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Amazon Nova Micro in Muse Code?

Turn project text into release notes, issue labels, and small code drafts with Amazon Nova Micro. Give it a focused file selection and one clearly defined result per request.

### Support ticket routing

Classify incoming ticket text into billing, access, technical, or other. Include a short supporting excerpt so a reviewer can check the label.

### Meeting summaries

Turn an existing meeting transcript into decisions, action items, and open questions. Preserve stated owners and deadlines, and mark missing details.

### Entity extraction

Extract names, organizations, dates, and reference numbers from messages into a consistent JSON structure.

### Support reply translation

Translate short replies between languages such as English, Spanish, French, and German while preserving product names, identifiers, and numbers.

### Answers from reference text

Draft answers from supplied help center passages. Require supporting excerpts and an explicit acknowledgment when the passages do not answer the question.

### Small coding tasks

Draft a focused function, explain a short code snippet, or propose examples for a small utility. Check the result with the project's tests.

### Content brainstorming

Generate subject lines, article titles, or outline ideas from a clear brief, with a fixed count and length for each suggestion.

### Customer reply drafts

Turn a customer's message and supplied policy text into a concise reply. Require the draft to stay within the policy and flag unanswered questions.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## Amazon Nova Micro in other agents

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

## More Muse Code guides

- [Amazon Nova Lite 1.0](https://spiral.ai/integrations/muse-code/amazon-nova-lite-1-0)
- [Amazon Nova Premier 1.0](https://spiral.ai/integrations/muse-code/amazon-nova-premier-1-0)
- [Amazon Nova 2 Lite](https://spiral.ai/integrations/muse-code/amazon-nova-2-lite)
- [Amazon Nova Pro 1.0](https://spiral.ai/integrations/muse-code/amazon-nova-pro-1-0)
- [Aion-RP 1.0 (8B)](https://spiral.ai/integrations/muse-code/aion-rp-1-0-8b)
- [Beam 1.0 501B A23B](https://spiral.ai/integrations/muse-code/beam-1-0-501b-a23b)

## Questions about Amazon Nova Micro in Muse Code

**Can Muse Code use Amazon Nova Micro?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Amazon Nova Micro like any built-in tool.

**How much does Amazon Nova Micro cost in Muse Code?**

Up to $0.000748 per run at the default inputs. $0.0455 per 1M input tokens, $0.182 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

**Do I need an OpenRouter account to use Amazon Nova Micro in Muse Code?**

No. Spiral runs Amazon Nova Micro on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Amazon Nova Micro in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while Amazon Nova Micro runs?**

Amazon Nova Micro runs in the background. Muse Code starts the run, checks on it and gives you the text, json when it's ready.

**What is Amazon Nova Micro best at?**

Use it for text summarization, translation, classification, and short conversations. AWS also identifies simple coding and brainstorming as suitable tasks.

**Can Amazon Nova Micro analyze images or recordings?**

Amazon Nova Micro accepts text only. Provide an existing transcript or extracted text when the original material is a recording or scanned document.

**How much text can Amazon Nova Micro work with?**

It has a 128K-token context window. For a long document, specify the sections to examine and the exact questions to answer.

**Which languages is Amazon Nova Micro optimized for?**

AWS lists English, German, Spanish, French, Italian, Japanese, Korean, Arabic, Simplified Chinese, Russian, Hindi, Portuguese, Dutch, Turkish, and Hebrew. State the target language explicitly when requesting a translation.

**How do I ask Amazon Nova Micro for JSON?**

Define the required keys, allowed values, and how to represent missing information. Explicitly request one JSON object with no surrounding explanation.

