[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [Qwen3 235B A22B Instruct 2507](https://spiral.ai/integrations/muse-code/qwen3-235b-a22b-instruct-2507)

# How to Use Qwen3 235B A22B Instruct 2507 in Muse Code

Qwen3 235B A22B Instruct 2507 suits long-document analysis, multilingual writing, coding, and tool-based tasks. Unlike the original Qwen3 235B A22B, it only uses non-thinking mode and has a published native context of 262,144 tokens.

|  |  |
| --- | --- |
| Model | Qwen3 235B A22B Instruct 2507 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.004267 per run at the default inputs. $0.182 per 1M input tokens, $1.04 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3 235B A22B Instruct 2507 in Muse Code

- Use Qwen3 235B A22B Instruct 2507 to trace authentication through this repository. Read the relevant code and tests, explain the request flow, and cite file paths for each stage.
- Use Qwen3 235B A22B Instruct 2507 to investigate the failing tests in this project. Reproduce the failure, propose the smallest justified patch, and run the relevant tests.
- Use Qwen3 235B A22B Instruct 2507 to compare the API documentation with the implementation. List mismatches with file references and draft corrections supported by the code.
- Use Qwen3 235B A22B Instruct 2507 to review the current diff for behavioral regressions. Explain each finding with a concrete input, expected result, and relevant code location.
- Use Qwen3 235B A22B Instruct 2507 to translate this project's English help strings into Spanish. Preserve interpolation tokens, follow the existing glossary, and flag ambiguous source wording.

## How to set up Qwen3 235B A22B Instruct 2507 in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse Code 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 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 Qwen3 235B A22B Instruct 2507**: 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": "qwen/qwen3-235b-a22b-2507",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse Code finds Qwen3 235B A22B Instruct 2507 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## Qwen3 235B A22B Instruct 2507 tools and prices

- [Qwen: Qwen3 235B A22B Instruct 2507](https://spiral.ai/tools/openrouter/qwen/qwen3-235b-a22b-2507) (OpenRouter): Up to $0.004267 per run at the default inputs. $0.182 per 1M input tokens, $1.04 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with Qwen3 235B A22B Instruct 2507 in Muse Code?

Turn project code and documentation into explanations, focused patches, and review notes with Qwen3 235B A22B Instruct 2507. Give the agent a concrete failure or question and require evidence from the files it inspects.

### Compare long policy documents

Ask Qwen3 235B A22B Instruct 2507 to compare supplied policy text, identify conflicting clauses, and cite section headings for each finding.

### Draft multilingual support replies

Use Qwen3 235B A22B Instruct 2507 to draft responses from a supplied support policy, preserving product names and matching the customer's language.

### Turn prose into structured records

Give Qwen3 235B A22B Instruct 2507 a record format and source text. Request extracted values, supporting excerpts, and null values for missing information.

### Explain unfamiliar code

Ask Qwen3 235B A22B Instruct 2507 to trace supplied code, explain dependencies, and identify assumptions that need checking before a change.

### Prepare focused bug fixes

Use Qwen3 235B A22B Instruct 2507 to propose a small patch from a reproducible failure, then check the result with relevant tests.

### Write evidence-based briefs

Ask Qwen3 235B A22B Instruct 2507 to synthesize supplied reports into a brief with source references, disagreements, and unanswered questions.

### Localize product copy

Use Qwen3 235B A22B Instruct 2507 to adapt supplied copy for a named audience and language while preserving a glossary and required claims.

### Prepare tool-assisted answers

Have Qwen3 235B A22B Instruct 2507 use the agent's available lookup tools to gather evidence, then produce an answer that identifies its sources.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## Qwen3 235B A22B Instruct 2507 in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-235b-a22b-instruct-2507)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-235b-a22b-instruct-2507)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-235b-a22b-instruct-2507)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-235b-a22b-instruct-2507)
- [Cline](https://spiral.ai/integrations/cline/qwen3-235b-a22b-instruct-2507)
- [Codex](https://spiral.ai/integrations/codex/qwen3-235b-a22b-instruct-2507)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-235b-a22b-instruct-2507)
- [Devin](https://spiral.ai/integrations/devin/qwen3-235b-a22b-instruct-2507)
- [dots](https://spiral.ai/integrations/dots/qwen3-235b-a22b-instruct-2507)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-235b-a22b-instruct-2507)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-235b-a22b-instruct-2507)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-235b-a22b-instruct-2507)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-235b-a22b-instruct-2507)
- [goose](https://spiral.ai/integrations/goose/qwen3-235b-a22b-instruct-2507)
- [Grok](https://spiral.ai/integrations/grok/qwen3-235b-a22b-instruct-2507)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-235b-a22b-instruct-2507)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-235b-a22b-instruct-2507)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-235b-a22b-instruct-2507)
- [Manus](https://spiral.ai/integrations/manus/qwen3-235b-a22b-instruct-2507)
- [Muse](https://spiral.ai/integrations/muse/qwen3-235b-a22b-instruct-2507)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-235b-a22b-instruct-2507)
- [Notion](https://spiral.ai/integrations/notion/qwen3-235b-a22b-instruct-2507)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-235b-a22b-instruct-2507)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-235b-a22b-instruct-2507)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-235b-a22b-instruct-2507)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-235b-a22b-instruct-2507)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-235b-a22b-instruct-2507)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-235b-a22b-instruct-2507)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-235b-a22b-instruct-2507)

## More Muse Code guides

- [Qwen3 14B](https://spiral.ai/integrations/muse-code/qwen3-14b)
- [Qwen3 235B A22B Thinking 2507](https://spiral.ai/integrations/muse-code/qwen3-235b-a22b-thinking-2507)
- [Qwen2.5-VL 72B Instruct](https://spiral.ai/integrations/muse-code/qwen2-5-vl-72b-instruct)
- [Qwen3 30B A3B](https://spiral.ai/integrations/muse-code/qwen3-30b-a3b)
- [Qwen2.5 Coder 32B Instruct](https://spiral.ai/integrations/muse-code/qwen2-5-coder-32b-instruct)
- [Qwen3 30B A3B Instruct 2507](https://spiral.ai/integrations/muse-code/qwen3-30b-a3b-instruct-2507)

## Questions about Qwen3 235B A22B Instruct 2507 in Muse Code

**Can Muse Code use Qwen3 235B A22B Instruct 2507?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Qwen3 235B A22B Instruct 2507 like any built-in tool.

**How much does Qwen3 235B A22B Instruct 2507 cost in Muse Code?**

Up to $0.004267 per run at the default inputs. $0.182 per 1M input tokens, $1.04 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 235B A22B Instruct 2507 in Muse Code?**

No. Spiral runs Qwen3 235B A22B Instruct 2507 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 235B A22B Instruct 2507 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 235B A22B Instruct 2507 runs?**

Qwen3 235B A22B Instruct 2507 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 235B A22B Instruct 2507 good for?**

It suits text comprehension, multilingual writing, coding, logical reasoning, and tasks that use tools. Practical starting points include comparing long documents, drafting localized support responses, and explaining code.

**Can Qwen3 235B A22B Instruct 2507 switch into thinking mode?**

No. It only supports non-thinking mode and does not generate separate think blocks. Ask for an explanation when you need one, but do not treat that as enabling a different reasoning mode.

**How much text can Qwen3 235B A22B Instruct 2507 handle?**

Qwen publishes a native context length of 262,144 tokens. Its documented 1,010,000-token extension requires a separate configuration, so that figure should not be treated as the default.

**How long should I let Qwen3 235B A22B Instruct 2507 answer?**

Qwen recommends allowing 16,384 output tokens for most queries. That is an allowance, not a target answer length or a published maximum; specify a shorter word count when you want a brief response.

**Which languages does Qwen3 support?**

Qwen documents 119 languages and dialects, including English, Chinese, Spanish, Arabic, Japanese, and Korean. For translation work, specify the target language, audience, and terms that must stay unchanged.

