[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [Qwen3 30B A3B Instruct 2507](https://spiral.ai/integrations/muse-code/qwen3-30b-a3b-instruct-2507)

# How to Use Qwen3 30B A3B Instruct 2507 in Muse Code

Qwen3 30B A3B Instruct 2507 suits document analysis, writing, coding, and tool-driven tasks with a native 262,144-token context. Unlike Qwen3 30B A3B Thinking 2507, it produces answers without a separate thinking mode.

|  |  |
| --- | --- |
| Model | Qwen3 30B A3B Instruct 2507 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001603 per run at the default inputs. $0.13 per 1M input tokens, $0.39 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3 30B A3B Instruct 2507 in Muse Code

- Use Qwen3 30B A3B Instruct 2507 to review the current diff and relevant callers. Identify concrete failure cases, cite file locations, and suggest the smallest check for each.
- Use Qwen3 30B A3B Instruct 2507 to compare the README with the command-line parser. List documented flags that differ from the code, then propose corrected wording.
- Use Qwen3 30B A3B Instruct 2507 to trace the failing test through the implementation. Propose a minimal fix, run the relevant test, and report what the result establishes.
- Use Qwen3 30B A3B Instruct 2507 to translate the English help strings into Spanish. Follow the existing glossary and preserve interpolation tokens and command names.
- Use Qwen3 30B A3B Instruct 2507 to explain the request-validation path using the relevant source files. Return a concise sequence of functions, validation rules, and error responses.

## How to set up Qwen3 30B A3B 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 30B A3B 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/qwen3-30b-a3b-instruct-2507",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse Code finds Qwen3 30B A3B Instruct 2507 on Spiral, shows the price and runs it.

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

## Qwen3 30B A3B Instruct 2507 tools and prices

- [Qwen: Qwen3 30B A3B Instruct 2507](https://spiral.ai/tools/openrouter/qwen/qwen3-30b-a3b-instruct-2507) (OpenRouter): Up to $0.001603 per run at the default inputs. $0.13 per 1M input tokens, $0.39 per 1M output tokens.

## Settings you can ask for

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

## What can you do with Qwen3 30B A3B Instruct 2507 in Muse Code?

Turn project code and documentation into focused reviews, patches, and explanations with Qwen3 30B A3B Instruct 2507. Give it relevant files, an explicit acceptance criterion, and a way to check the result.

### Compare long documents

Ask Qwen3 30B A3B Instruct 2507 to compare supplied policy documents, identify conflicting requirements, and quote the passages behind each finding.

### Review code changes

Use Qwen3 30B A3B Instruct 2507 to examine a patch alongside relevant code, explain possible failures, and suggest focused checks.

### Draft support replies

Give Qwen3 30B A3B Instruct 2507 a customer message and approved policy text. Request a reply that cites the policy and identifies missing information.

### Localize help content

Ask Qwen3 30B A3B Instruct 2507 to translate help articles using a supplied glossary while preserving product names and instructions.

### Extract records from text

Have Qwen3 30B A3B Instruct 2507 turn supplied messages into structured records with explicit rules for missing values and supporting excerpts.

### Produce recurring research briefs

Use Qwen3 30B A3B Instruct 2507 to summarize newly retrieved source text, separate reported changes from commentary, and retain source links.

### Revise drafts against a brief

Ask Qwen3 30B A3B Instruct 2507 to rewrite a draft for a specific audience, length, and tone while preserving supplied facts.

### Explain verified calculations

Give Qwen3 30B A3B Instruct 2507 calculator or code results and ask for an explanation of the assumptions, units, and conclusions.

## Overview

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

## Qwen3 30B A3B Instruct 2507 in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-30b-a3b-instruct-2507)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-30b-a3b-instruct-2507)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-30b-a3b-instruct-2507)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-30b-a3b-instruct-2507)
- [Cline](https://spiral.ai/integrations/cline/qwen3-30b-a3b-instruct-2507)
- [Codex](https://spiral.ai/integrations/codex/qwen3-30b-a3b-instruct-2507)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-30b-a3b-instruct-2507)
- [Devin](https://spiral.ai/integrations/devin/qwen3-30b-a3b-instruct-2507)
- [dots](https://spiral.ai/integrations/dots/qwen3-30b-a3b-instruct-2507)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-30b-a3b-instruct-2507)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-30b-a3b-instruct-2507)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-30b-a3b-instruct-2507)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-30b-a3b-instruct-2507)
- [goose](https://spiral.ai/integrations/goose/qwen3-30b-a3b-instruct-2507)
- [Grok](https://spiral.ai/integrations/grok/qwen3-30b-a3b-instruct-2507)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-30b-a3b-instruct-2507)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-30b-a3b-instruct-2507)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-30b-a3b-instruct-2507)
- [Manus](https://spiral.ai/integrations/manus/qwen3-30b-a3b-instruct-2507)
- [Muse](https://spiral.ai/integrations/muse/qwen3-30b-a3b-instruct-2507)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-30b-a3b-instruct-2507)
- [Notion](https://spiral.ai/integrations/notion/qwen3-30b-a3b-instruct-2507)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-30b-a3b-instruct-2507)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-30b-a3b-instruct-2507)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-30b-a3b-instruct-2507)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-30b-a3b-instruct-2507)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-30b-a3b-instruct-2507)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-30b-a3b-instruct-2507)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-30b-a3b-instruct-2507)

## More Muse Code guides

- [Qwen3 30B A3B](https://spiral.ai/integrations/muse-code/qwen3-30b-a3b)
- [Qwen3 32B](https://spiral.ai/integrations/muse-code/qwen3-32b)
- [Qwen3 235B A22B Thinking 2507](https://spiral.ai/integrations/muse-code/qwen3-235b-a22b-thinking-2507)
- [Qwen3 Coder 30B A3B Instruct](https://spiral.ai/integrations/muse-code/qwen3-coder-30b-a3b-instruct)
- [Qwen3 235B A22B Instruct 2507](https://spiral.ai/integrations/muse-code/qwen3-235b-a22b-instruct-2507)
- [Qwen3 Coder 480B A35B](https://spiral.ai/integrations/muse-code/qwen3-coder-480b-a35b)

## Questions about Qwen3 30B A3B Instruct 2507 in Muse Code

**Can Muse Code use Qwen3 30B A3B Instruct 2507?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Qwen3 30B A3B Instruct 2507 like any built-in tool.

**How much does Qwen3 30B A3B Instruct 2507 cost in Muse Code?**

Up to $0.001603 per run at the default inputs. $0.13 per 1M input tokens, $0.39 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 30B A3B Instruct 2507 in Muse Code?**

No. Spiral runs Qwen3 30B A3B 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 30B A3B 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 30B A3B Instruct 2507 runs?**

Qwen3 30B A3B 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 30B A3B Instruct 2507 useful for?**

Use it to analyze supplied text, draft and revise writing, work through coding tasks, and interpret tool results. Qwen reports improvements in instruction following, text comprehension, coding, and tool use.

**Does Qwen3 30B A3B Instruct 2507 have a thinking mode?**

It supports only non-thinking mode and does not produce separate thinking blocks. You can still request an explanation, but that does not enable the dedicated mode used by Qwen3 30B A3B Thinking 2507.

**How much text can Qwen3 30B A3B Instruct 2507 handle?**

Its native context length is 262,144 tokens. Qwen recommends a 16,384-token output budget for most queries; that is guidance for generation length, not a stated hard output maximum.

**Which languages does Qwen3 30B A3B Instruct 2507 support?**

Qwen lists support for 119 languages and dialects across Qwen3, including English, Spanish, Chinese, Arabic, Japanese, and Korean. Specify the target language and provide a glossary when particular terms must stay consistent.

**Which sampling settings should I start with?**

Qwen's Instruct 2507 examples use temperature 0.7, top-p 0.8, and top-k 20. Use those as a starting point and compare results on representative tasks before changing them.

