[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Muse Spark 1.2 Contributor](https://spiral.ai/integrations/instinct/muse-spark-1-2-contributor)

# How to Use Muse Spark 1.2 Contributor in Instinct

Muse Spark 1.2 Contributor suits complex debugging, codebase analysis, and multi-step agents. Unlike Muse Spark 1.2 in Standard mode, its prompts and responses may be used to train future Meta models.

|  |  |
| --- | --- |
| Model | Muse Spark 1.2 Contributor |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.00107 per run at the default inputs. $0.13 per 1M input tokens, $0.26 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Muse Spark 1.2 Contributor in Instinct

- Use Muse Spark 1.2 Contributor on each run to classify newly received requests as bug report, feature request, or how-to question. Return the request identifier, category, and a short explanation.
- Use Muse Spark 1.2 Contributor on each run to analyze new error reports. Group reports with the same symptoms and list the evidence an engineer would need to reproduce each problem.
- Use Muse Spark 1.2 Contributor on each run to summarize newly received product demonstration videos. Describe each demonstrated workflow and list questions the footage leaves unanswered.
- Use Muse Spark 1.2 Contributor on each run to extract dates, organizations, and stated outcomes from new reports. Return consistent JSON records and mark missing values as null.
- Use Muse Spark 1.2 Contributor on each run to analyze newly received chart images. Report the visible measurements, units, and main comparisons without estimating unreadable values.

## How to set up Muse Spark 1.2 Contributor in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 Spark 1.2 Contributor**: 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-spark-1.2-contributor",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Muse Spark 1.2 Contributor on Spiral, shows the price and runs it.

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

## Muse Spark 1.2 Contributor tools and prices

- [Meta: Muse Spark 1.2 Contributor](https://spiral.ai/tools/openrouter/meta/muse-spark-1.2-contributor) (OpenRouter): Up to $0.00107 per run at the default inputs. $0.13 per 1M input tokens, $0.26 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 Spark 1.2 Contributor in Instinct?

Turn recurring reports, incoming requests, and demonstration videos into consistent summaries with Muse Spark 1.2 Contributor. Define what each run should examine and the exact result it should return.

### Debug a problem across a repository

Trace an error through related modules, propose a fix, and check the behavior that originally failed.

### Plan and carry out a refactor

Map the affected code, sequence changes across modules, and verify that the intended behavior survives.

### Build a working prototype

Turn a detailed specification into a repository with application code and checks for its main behaviors.

### Turn a visual reference into interface code

Use an image or demonstration video to guide layout, hierarchy, and interaction code.

### Explain a chart

Extract visible values and units, then write a comparison grounded in the chart.

### Summarize a demonstration video

Describe the sequence of actions and answer specific questions about what happens in the footage.

### Extract structured records

Turn unstructured reports into JSON records with a defined set of fields.

### Categorize incoming requests

Assign requests to predefined categories and return consistent structured labels.

## Overview

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

## Muse Spark 1.2 Contributor in other agents

- [Amp](https://spiral.ai/integrations/amp/muse-spark-1-2-contributor)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/muse-spark-1-2-contributor)
- [Claude](https://spiral.ai/integrations/claude-desktop/muse-spark-1-2-contributor)
- [Claude Code](https://spiral.ai/integrations/claude-code/muse-spark-1-2-contributor)
- [Cline](https://spiral.ai/integrations/cline/muse-spark-1-2-contributor)
- [Codex](https://spiral.ai/integrations/codex/muse-spark-1-2-contributor)
- [Cursor](https://spiral.ai/integrations/cursor/muse-spark-1-2-contributor)
- [Devin](https://spiral.ai/integrations/devin/muse-spark-1-2-contributor)
- [dots](https://spiral.ai/integrations/dots/muse-spark-1-2-contributor)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/muse-spark-1-2-contributor)
- [Gemini](https://spiral.ai/integrations/gemini/muse-spark-1-2-contributor)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/muse-spark-1-2-contributor)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/muse-spark-1-2-contributor)
- [goose](https://spiral.ai/integrations/goose/muse-spark-1-2-contributor)
- [Grok](https://spiral.ai/integrations/grok/muse-spark-1-2-contributor)
- [Grok Build](https://spiral.ai/integrations/grok-build/muse-spark-1-2-contributor)
- [Hermes](https://spiral.ai/integrations/hermes/muse-spark-1-2-contributor)
- [Manus](https://spiral.ai/integrations/manus/muse-spark-1-2-contributor)
- [Muse](https://spiral.ai/integrations/muse/muse-spark-1-2-contributor)
- [Muse Code](https://spiral.ai/integrations/muse-code/muse-spark-1-2-contributor)
- [n8n](https://spiral.ai/integrations/n8n/muse-spark-1-2-contributor)
- [Notion](https://spiral.ai/integrations/notion/muse-spark-1-2-contributor)
- [OpenClaw](https://spiral.ai/integrations/openclaw/muse-spark-1-2-contributor)
- [opencode](https://spiral.ai/integrations/opencode/muse-spark-1-2-contributor)
- [Perplexity](https://spiral.ai/integrations/perplexity/muse-spark-1-2-contributor)
- [Raycast](https://spiral.ai/integrations/raycast/muse-spark-1-2-contributor)
- [VS Code](https://spiral.ai/integrations/vscode/muse-spark-1-2-contributor)
- [Windsurf](https://spiral.ai/integrations/windsurf/muse-spark-1-2-contributor)
- [Zapier](https://spiral.ai/integrations/zapier/muse-spark-1-2-contributor)

## More Instinct guides

- [Muse Spark 1.2](https://spiral.ai/integrations/instinct/muse-spark-1-2)
- [Muse Spark 1.3](https://spiral.ai/integrations/instinct/muse-spark-1-3)
- [Muse Spark 1.1](https://spiral.ai/integrations/instinct/muse-spark-1-1)
- [Muse Spark 1.3 Contributor](https://spiral.ai/integrations/instinct/muse-spark-1-3-contributor)
- [Muse Glimmer 30B (batch)](https://spiral.ai/integrations/instinct/muse-glimmer-30b-batch)
- [Muse Spark Open](https://spiral.ai/integrations/instinct/muse-spark-open)

## Questions about Muse Spark 1.2 Contributor in Instinct

**Can Instinct use Muse Spark 1.2 Contributor?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Muse Spark 1.2 Contributor like any built-in tool.

**How much does Muse Spark 1.2 Contributor cost in Instinct?**

Up to $0.00107 per run at the default inputs. $0.13 per 1M input tokens, $0.26 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an OpenRouter account to use Muse Spark 1.2 Contributor in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Muse Spark 1.2 Contributor on its own OpenRouter account.

**How long does it take to set up Muse Spark 1.2 Contributor in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Muse Spark 1.2 Contributor runs?**

Muse Spark 1.2 Contributor runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is Muse Spark 1.2 Contributor best suited for?**

Start with complex debugging, understanding a large codebase, and coding tasks that require several rounds of work. Muse Spark 1.2 was also trained on generating complete repositories and larger projects.

**How much context can Muse Spark 1.2 Contributor handle?**

Its context window is 1,048,576 tokens. That gives you room to provide substantial code or reference material for analysis.

**Does Muse Spark 1.2 Contributor generate images or videos?**

It returns text. It can analyze images and videos or write code based on a visual reference, but it does not return generated image or video media.

**What does Contributor mean?**

Content sent in Contributor mode may be used to train future Meta models. Meta says content sent in Standard mode is not used for that training.

**Can Muse Spark 1.2 Contributor read charts?**

Yes. Ask it to extract the relevant values, identify the units, and explain the comparison you care about.

