How to Use Muse Spark 1.2 in Windsurf
Muse Spark 1.2 is built for multi-file refactors, long debugging sessions, and turning visual references into code. It improves on Muse Spark 1.1 with a coding-focused update and a 1,048,576-token context window.
Prompts to try with Muse Spark 1.2 in Windsurf
Copy an example into Windsurf, or ask in your own words.
Use Muse Spark 1.2 with high reasoning effort to trace how this project handles expired sessions. Reproduce the reported logout loop, fix the cause, and run the relevant tests.
Use Muse Spark 1.2 to replace duplicated date-formatting code with one shared utility. Find every caller, preserve existing behavior, and report the checks you ran.
Use Muse Spark 1.2 to study this repository's data-access layer and plan its migration to the next major database library version. List dependencies between changes and a validation check for each stage.
Use Muse Spark 1.2 to implement the supplied screenshot using this project's existing components. Render the result, compare spacing and hierarchy with the reference, and correct visible mismatches.
Use Muse Spark 1.2 to investigate why this project's background job sometimes processes an event twice. Compare the retry path, acknowledgment timing, and restart behavior, then test the most likely cause.
How to set up Muse Spark 1.2 in Windsurf
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: ~/.config/devin/mcp_config.json on macOS and Linux, %APPDATA%\devin\mcp_config.json on Windows. Add this:
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.
devin mcp login spiral
- Check it
Spiral is listed under This computer in Customize › MCPs. From the terminal:
devin mcp list
Use the Spiral skill
- Send Windsurf 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 1.2
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-1.2", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Windsurf finds Muse Spark 1.2 on Spiral, shows the price and runs it.
Muse Spark 1.2 providers and prices
Spiral runs Muse Spark 1.2 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 Windsurf 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 1.2 is on its tool page: open its card above.
What can you do with Muse Spark 1.2 in Windsurf?
Muse Spark 1.2 can carry a refactor or debugging investigation across multiple files and turns. Give it the relevant project context and a concrete check for success.
Refactor across several files
Use Muse Spark 1.2 to trace a shared interface, update its callers, and check that the affected behavior still works.
Investigate a persistent bug
Give Muse Spark 1.2 the symptoms and relevant code, then work through competing explanations and test a targeted fix.
Plan a software migration
Ask Muse Spark 1.2 to compare architecture choices and order the changes so dependencies and validation are explicit.
Build from a visual reference
Have Muse Spark 1.2 translate a screenshot or demonstration video into interface code, then compare the rendered result with the reference.
Read charts and diagrams
Ask Muse Spark 1.2 to extract visible labels and values, explain relationships, and identify details that need a closer view.
Extract structured records
Use Muse Spark 1.2 to turn unstructured descriptions into JSON records with a defined schema for downstream processing.
Classify incoming requests
Have Muse Spark 1.2 assign predefined categories to support requests and return a consistent structure for review or routing.
Summarize recorded demonstrations
Ask Muse Spark 1.2 to explain what happens in a video, identify the relevant sequence of actions, and turn it into written instructions.
More on Muse Spark 1.2 and Windsurf
Overview
Muse Spark 1.2 in other agents
Questions about Muse Spark 1.2 in Windsurf
Can Windsurf use Muse Spark 1.2?
Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run Muse Spark 1.2 like any built-in tool.
How much does Muse Spark 1.2 cost in Windsurf?
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 Windsurf plan is separate.
Do I need an OpenRouter account to use Muse Spark 1.2 in Windsurf?
No. Spiral runs Muse Spark 1.2 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 1.2 in Windsurf?
About two minutes: add the server, then sign in, then check it.
Does Windsurf wait while Muse Spark 1.2 runs?
Muse Spark 1.2 runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.
What is Muse Spark 1.2 best suited for?
Multi-file refactors, long debugging sessions, and coding tasks that take several rounds of work. Meta describes it as a moderate improvement over Muse Spark 1.1.
How much context can Muse Spark 1.2 handle?
Its context window is 1,048,576 tokens. That is the context capacity, not a promise that every answer can be that long.
Can Muse Spark 1.2 generate images, video, or audio?
Its output is text, including code and structured JSON. It can analyze images, video, and audio, but does not return generated media.
When should I increase reasoning effort?
Use more reasoning for complex code generation, architecture tradeoffs, and planning with several dependent steps. Leave enough output budget for both internal reasoning and the final answer.
Should I lower temperature for more focused answers?
Meta recommends the default temperature of 1.0 for most work. Start by making the task, constraints, and expected answer more explicit.
Start using Muse Spark 1.2 in Windsurf
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Windsurf:
set up https://spiral.ai/SKILL.md


