How to Use Qwen3.5-27B in Muse Code
Qwen3.5-27B suits coding, multilingual writing, and long-document analysis. It uses a dense 27B design, with overall capabilities Alibaba describes as comparable to Qwen3.5-122B-A10B.
Prompts to try with Qwen3.5-27B in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use Qwen3.5-27B with thinking enabled and temperature 0.6 to investigate the failing tests in this project. Find the root cause, make the smallest justified patch, and run the relevant tests.
Use Qwen3.5-27B to review the current diff. Report only actionable bugs, cite file locations, and describe an input that would trigger each failure.
Use Qwen3.5-27B to trace authentication through this project's files. Explain token validation, expiration handling, and error paths, with references to the code.
Use Qwen3.5-27B to compare the implementation with the requirements in this repository. Return a table of satisfied requirements, gaps, and evidence.
Use Qwen3.5-27B to review the Spanish translations in this project. Preserve interpolation tokens and product names, flag terminology inconsistencies, and propose edits for Mexican Spanish.
How to set up Qwen3.5-27B in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse 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 Qwen3.5-27B
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": "qwen/qwen3.5-27b", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Muse Code finds Qwen3.5-27B on Spiral, shows the price and runs it.
Qwen3.5-27B providers and prices
Spiral runs Qwen3.5-27B through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.132916 per run at the default inputs. $0.2535 per 1M input tokens, $2.028 per 1M output tokens.
Settings you can ask for
Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 81920 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Qwen: Qwen3.5-27B is on its tool page: open its card above.
What can you do with Qwen3.5-27B in Muse Code?
Turn project context into code fixes, reviews, and technical explanations with Qwen3.5-27B. Give the agent relevant files, expected behavior, and a specific way to check the result.
Fix a reproducible bug
Give Qwen3.5-27B the failing behavior, relevant code, and expected result. Request a small patch and a regression check.
Review a code change
Ask Qwen3.5-27B to inspect a diff for concrete failures, explain each finding, and suggest a test that would expose it.
Compare technical proposals
Have Qwen3.5-27B compare supplied specifications against the same requirements, citing passages for each conclusion.
Localize customer responses
Use Qwen3.5-27B to rewrite approved support language for a named locale while preserving product names and policy details.
Extract structured records
Ask Qwen3.5-27B to turn supplied text into JSON with defined keys, explicit missing values, and supporting excerpts.
Check a mathematical solution
Give Qwen3.5-27B a problem and proposed solution. Request the first incorrect step, a correction, and a clearly marked final answer.
Summarize recurring updates
Have Qwen3.5-27B compare supplied updates with the previous summary and report changed commitments, unresolved questions, and supporting evidence.
More on Qwen3.5-27B and Muse Code
Overview
Qwen3.5-27B in other agents
Questions about Qwen3.5-27B in Muse Code
Can Muse Code use Qwen3.5-27B?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Qwen3.5-27B like any built-in tool.
How much does Qwen3.5-27B cost in Muse Code?
Up to $0.013857 per run at the default inputs. $0.338 per 1M input tokens, $3.38 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 Qwen3.5-27B in Muse Code?
No. Spiral runs Qwen3.5-27B on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen3.5-27B in Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while Qwen3.5-27B runs?
Qwen3.5-27B runs in the background. Muse Code starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen3.5-27B useful for?
Consider it for code changes, multilingual writing, and analysis across long documents. Give it a concrete deliverable, such as a patch, translated response, or comparison table.
How does Qwen3.5-27B compare with Qwen3.5-122B-A10B?
Qwen3.5-27B uses a dense 27B design. Alibaba describes its overall capabilities as comparable to Qwen3.5-122B-A10B; that does not establish equal results on every task.
How much context does Qwen3.5-27B support?
Its native context window is 262,144 tokens. For document comparisons, identify each source and ask it to cite the relevant sections.
Can Qwen3.5-27B work in multiple languages?
Qwen reports support for 201 languages and dialects. Specify the target language, regional wording, and terms that must stay unchanged.
Which settings should I try for coding?
Qwen recommends thinking enabled with temperature 0.6, top-p 0.95, and top-k 20 for precise coding tasks.
Start using Qwen3.5-27B in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


