[Integrations](https://spiral.ai/integrations) › [Zapier](https://spiral.ai/integrations/zapier) › [Muse Ember](https://spiral.ai/integrations/zapier/muse-ember)

# How to Use Muse Ember in Zapier

Muse Ember handles focused coding tasks, routing, and document extraction. Choose it for repeated execution; Muse Spark and Muse Wonder are better choices for hard one-shot coding and knowledge-heavy questions.

|  |  |
| --- | --- |
| Model | Muse Ember |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Muse Ember in Zapier

- Each morning, use Muse Ember to classify newly received support tickets as billing, bug, or feature request. Report ticket numbers, categories, and supporting excerpts; flag unclear cases.
- At the end of each day, use Muse Ember to summarize the report text received that day. Give each report the same headings: findings, decisions, and open questions.
- Every hour, use Muse Ember to route new requests to the handlers in the supplied responsibility list. Return the request number, destination, and a brief reason.
- Each evening, use Muse Ember to extract invoice numbers, issue dates, and totals from newly received invoice text. Include source references and mark missing information explicitly.
- Each week, use Muse Ember to normalize newly received vendor records according to the supplied rules. Report converted records and ambiguous entries separately.

## How to set up Muse Ember in Zapier

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

### Use the Spiral skill

1. **Send Zapier 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 an MCP Client connection**: In Zapier open Apps, click Add connection and search for MCP Client. Fill in the form:

```text
https://api.spiral.ai/mcp
```

2. **Sign in to Spiral and approve**: Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Zapier never sees it, and you can remove it under Settings › Connected apps in the console.

3. **Run a Spiral tool in a Zap**: Add an MCP Client step to a Zap and choose the Run Tool action with your Spiral connection. Pick a tool: `discover` finds the right model for a task, `estimate_cost` prices it and `run` runs it. For example, `run` with:

```json
{
  "provider": "fal",
  "model": "fal-ai/flux/schnell",
  "input": { "prompt": "a lighthouse at dawn" },
  "wait": true
}
```

4. **Run Muse Ember in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Muse Ember, prices it and runs it each time the step fires.

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

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

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

## Muse Ember tools and prices

- [Meta: Muse Ember](https://spiral.ai/tools/openrouter/meta/muse-ember) (OpenRouter): Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| 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. 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). |

## What can you do with Muse Ember in Zapier?

Process recurring queues of tickets, records, and document text with Muse Ember. Use a fixed task and reporting structure so each run produces comparable results.

### Focused code repairs

Give Muse Ember a failing check, the relevant code, and a narrow acceptance criterion. Ask for a targeted fix and the verification result.

### Bounded code migrations

Use Muse Ember to port one function or module against a supplied reference and test suite. Define the interfaces and required behavior before requesting the change.

### Support ticket classification

Have Muse Ember assign each ticket to a defined category and include a short supporting excerpt for review.

### Request routing

Give Muse Ember the available handlers and their responsibilities. Ask it to select a destination for each incoming request and explain the selection briefly.

### Document extraction

Ask Muse Ember to extract dates, names, obligations, or totals from supplied document text into a consistent JSON structure, with source references and missing values marked explicitly.

### Document summaries

Use Muse Ember to summarize each supplied report with the same headings: findings, decisions, open questions, and supporting passages.

### Record normalization

Have Muse Ember convert inconsistent text records into a defined structure. Supply normalization rules and require ambiguous entries to be flagged.

## Overview

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

## Muse Ember in other agents

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

## More Zapier guides

- [Motif 3](https://spiral.ai/integrations/zapier/motif-3)
- [Muse Glimmer 30B](https://spiral.ai/integrations/zapier/muse-glimmer-30b)
- [Morph V3 Large (batch)](https://spiral.ai/integrations/zapier/morph-v3-large-batch)
- [Muse Glimmer 30B (batch)](https://spiral.ai/integrations/zapier/muse-glimmer-30b-batch)
- [Morph V3 Large](https://spiral.ai/integrations/zapier/morph-v3-large)
- [Muse Spark 1.1](https://spiral.ai/integrations/zapier/muse-spark-1-1)

## Questions about Muse Ember in Zapier

**Can Zapier use Muse Ember?**

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

**How much does Muse Ember cost in Zapier?**

Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Zapier plan is separate.

**Do I need an OpenRouter account to use Muse Ember in Zapier?**

No. Spiral runs Muse Ember 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 Ember in Zapier?**

About two minutes: add an MCP Client connection, then sign in to Spiral and approve, then run a Spiral tool in a Zap.

**Does Zapier wait while Muse Ember runs?**

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

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

Use it for focused work you repeat: coding subtasks, request routing, document summaries, and extracting information into a consistent structure.

**When should I choose Muse Spark or Muse Wonder instead?**

Meta recommends them for hard one-shot coding problems, knowledge-heavy questions, and visual coding. Give Muse Ember a narrower task when the broader problem needs those capabilities.

**How much text can Muse Ember handle?**

Meta documents a 1,048,576-token context window and up to 524,288 output tokens. Internal reasoning also consumes the output budget, so that maximum is not a promise of an equally long visible answer.

**Can Muse Ember return structured JSON?**

Yes. Use schema-constrained output for extraction and classification tasks that need a consistent JSON structure.

**How much reasoning should I use?**

Start with the lowest effort that passes your task checks. Leave enough output budget for both internal reasoning and the answer you need.

