How to Use Muse Spark 1.1 in VS Code
Muse Spark 1.1 suits codebase debugging, visual analysis, and tasks that need several tool calls. Compared with the original Muse Spark, it improves coding on large codebases and can plan work and delegate tasks.
Prompts to try with Muse Spark 1.1 in VS Code
Copy an example into VS Code, or ask in your own words.
Use Muse Spark 1.1 to investigate the failing tests in this project. Reproduce the failure, trace the cause, make the smallest justified fix, and report which checks passed.
Use Muse Spark 1.1 to review the current diff against the surrounding code. Report concrete bugs with file locations, a failure scenario, and a suggested correction.
Use Muse Spark 1.1 to compare the reference screenshot in this project with the current interface. Implement the visible layout differences and verify the result in the browser.
Use Muse Spark 1.1 to map how authentication works across this repository. Cite the relevant files, trace one successful request, and identify where expired credentials are handled.
Use Muse Spark 1.1 to plan the dependency upgrade described in the project issue. Identify affected code, order the changes by dependency, implement them, and run the relevant checks.
How to set up Muse Spark 1.1 in VS Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to VS Code on the console's Agents & MCP page, or run:
code --add-mcp '{"name":"spiral","type":"http","url":"https://api.spiral.ai/mcp"}' - Sign in
VS Code asks you to sign in when it first starts the server: sign in to Spiral and click Authorize. No API key. Run MCP: List Servers from the Command Palette to check that Spiral is running.
Use the Spiral skill
- Send VS Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Muse Spark 1.1
One request; the result comes back by polling or a webhook.
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-1.1", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: VS Code finds Muse Spark 1.1 on Spiral, shows the price and runs it.
Muse Spark 1.1 providers and prices
Spiral runs Muse Spark 1.1 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.022688 per run at the default inputs. $1.625 per 1M input tokens, $5.525 per 1M output tokens.
Settings you can ask for
Ask VS Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 943718 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Reasoning effort | minimal, low, medium, high, or xhigh | medium | How much the model reasons. |
| Repetition penalty | 0 to 2 |
Every API field of Meta: Muse Spark 1.1 is on its tool page: open its card above.
What can you do with Muse Spark 1.1 in VS Code?
Muse Spark 1.1 can turn a bug report or feature request into code changes across a repository. Give it reproduction steps and acceptance checks so it can investigate, edit, and verify the result.
Diagnose a codebase bug
Trace a reported failure through related code, propose a fix, and check it against the reproduction steps.
Review a proposed code change
Inspect a patch alongside surrounding code and identify concrete defects, missing checks, and changes that need testing.
Build from a screenshot
Turn a reference screenshot into interface code, then compare the implementation with the reference.
Answer questions across lengthy material
Bring related specifications or documents into context and ask for an answer with supporting passages and unresolved conflicts.
Extract product information
Convert unstructured product descriptions into consistent records, keeping missing details explicit.
Classify incoming requests
Assign requests to a fixed set of categories and return a short explanation for each label.
Coordinate a task with dependencies
Break an objective into focused tasks, identify dependencies, and combine the results into a final deliverable.
More on Muse Spark 1.1 and VS Code
Overview
Muse Spark 1.1 in other agents
Questions about Muse Spark 1.1 in VS Code
Can VS Code use Muse Spark 1.1?
Yes. Add Spiral to VS Code as an MCP server, and VS Code can find and run Muse Spark 1.1 like any built-in tool.
How much does Muse Spark 1.1 cost in VS Code?
Up to $0.022688 per run at the default inputs. $1.625 per 1M input tokens, $5.525 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your VS Code plan is separate.
Do I need an OpenRouter account to use Muse Spark 1.1 in VS Code?
No. Spiral runs Muse Spark 1.1 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 Spark 1.1 in VS Code?
About two minutes: add the hosted server, then sign in.
Does VS Code wait while Muse Spark 1.1 runs?
Muse Spark 1.1 runs in the background. VS Code starts the run, checks on it and gives you the text, json when it's ready.
What is Muse Spark 1.1 good at?
It suits debugging large codebases, analyzing visual material, and coordinating tasks across several tool calls. It can plan the work and delegate focused tasks.
How much context can Muse Spark 1.1 handle?
Its context window is 1,048,576 tokens. Treat that as a context capacity, not a promised answer length.
Can Muse Spark 1.1 generate images or video?
Its output is text. Use it to analyze visual material or write code and descriptions based on it.
What structured tasks suit Muse Spark 1.1?
Useful examples include extracting product details from text and assigning records to predefined categories. Specify the required structure and how missing information should be represented.
How should I choose reasoning effort?
Start with low effort for straightforward formatting and direct answers. For harder tasks, compare results at higher effort and leave enough output room for both internal reasoning and the final answer.
Start using Muse Spark 1.1 in VS Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into VS Code:
set up https://spiral.ai/SKILL.md


