[Integrations](https://spiral.ai/integrations) › [Manus](https://spiral.ai/integrations/manus) › [Qwen3 32B](https://spiral.ai/integrations/manus/qwen3-32b)

# How to Use Qwen3 32B in Manus

Qwen3 32B handles code generation, math problems, and multilingual text tasks. It combines thinking and non-thinking modes, so you can request deeper reasoning for difficult problems and direct answers for routine work.

|  |  |
| --- | --- |
| Model | Qwen3 32B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001495 per run at the default inputs. $0.104 per 1M input tokens, $0.364 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3 32B in Manus

- Use Qwen3 32B with deeper reasoning to check this calculation: a tank starts with 120 liters, gains 8 liters per minute, and loses 3 liters per minute. When does it reach 250 liters? Give the equation, result, and a short check.
- Use Qwen3 32B to translate this message into Spanish with a direct response: 'Your replacement is ready. Please confirm the delivery address.' Keep the tone polite and concise.
- Use Qwen3 32B with deeper reasoning to compare a queue and a stack for implementing browser back navigation. Give a small example and explain which operations the design needs.
- Use Qwen3 32B to practice a customer support conversation. Play a customer whose package arrived damaged, ask one question at a time, and assess my response after five turns.
- Use Qwen3 32B to rewrite my previous message as a clear, polite request in under 80 words. Answer directly and preserve all dates, names, and commitments.

## How to set up Qwen3 32B in Manus

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

### Use the Manus connector

1. **Add a custom MCP connector**: In Manus open Settings › Connectors (or the connectors icon under the chat box), then Add connectors › Custom MCP and Add MCP by URL. Name it Spiral, set Transport to HTTP and paste this Server URL:

```text
https://api.spiral.ai/mcp
```

2. **Sign in to Spiral and approve**: Manus asks you to sign in the first time it uses Spiral. Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Manus never sees it, and you can remove it under Settings › Connected apps in the console.

### Use the Spiral skill

1. **Send Manus 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 32B**: 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/qwen3-32b",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Manus finds Qwen3 32B on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/manus

## Qwen3 32B tools and prices

- [Qwen: Qwen3 32B](https://spiral.ai/tools/openrouter/qwen/qwen3-32b) (OpenRouter): Up to $0.001495 per run at the default inputs. $0.104 per 1M input tokens, $0.364 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 32B in Manus?

Qwen3 32B can help you solve math problems, translate messages, and work through technical questions in conversation. Request deeper reasoning for difficult problems and direct responses for routine language tasks.

### Debug a failing function

Provide the function, failing input, and expected result. Request a proposed fix and a regression test that exposes the original bug.

### Generate code from acceptance criteria

Describe the function signature, constraints, and edge cases. Ask for an implementation with examples covering empty inputs and boundary values.

### Check a mathematical solution

Supply the problem and your attempted solution. Ask where the reasoning first fails and request a corrected result with a short verification.

### Translate customer messages

Translate incoming messages into the team's working language while preserving product names, identifiers, and the customer's tone.

### Adapt support replies

Give the approved policy and the customer's question. Request a concise reply in the customer's language, with unanswered questions clearly identified.

### Compare technical approaches

Describe two implementations and the requirements they must meet. Ask for tradeoffs, conflicting constraints, and a recommendation tied to those requirements.

### Turn conversations into action lists

Provide a bounded conversation excerpt and request decisions, owners, and unresolved questions. Require supporting excerpts for each extracted action.

### Practice a support conversation

Describe a customer scenario and have Qwen3 32B play the customer across several turns. Finish by asking which questions clarified the problem and which assumptions remained.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Manus guides](https://spiral.ai/integrations/manus)

## Qwen3 32B in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-32b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-32b)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-32b)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-32b)
- [Cline](https://spiral.ai/integrations/cline/qwen3-32b)
- [Codex](https://spiral.ai/integrations/codex/qwen3-32b)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-32b)
- [Devin](https://spiral.ai/integrations/devin/qwen3-32b)
- [dots](https://spiral.ai/integrations/dots/qwen3-32b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-32b)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-32b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-32b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-32b)
- [goose](https://spiral.ai/integrations/goose/qwen3-32b)
- [Grok](https://spiral.ai/integrations/grok/qwen3-32b)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-32b)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-32b)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-32b)
- [Muse](https://spiral.ai/integrations/muse/qwen3-32b)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen3-32b)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-32b)
- [Notion](https://spiral.ai/integrations/notion/qwen3-32b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-32b)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-32b)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-32b)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-32b)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-32b)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-32b)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-32b)

## More Manus guides

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

## Questions about Qwen3 32B in Manus

**Can Manus use Qwen3 32B?**

Yes. Add Spiral to Manus as an MCP server, and Manus can find and run Qwen3 32B like any built-in tool.

**How much does Qwen3 32B cost in Manus?**

Up to $0.001495 per run at the default inputs. $0.104 per 1M input tokens, $0.364 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Manus plan is separate.

**Do I need an OpenRouter account to use Qwen3 32B in Manus?**

No. Spiral runs Qwen3 32B 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 32B in Manus?**

About two minutes: add a custom MCP connector, then sign in to Spiral and approve.

**Does Manus wait while Qwen3 32B runs?**

Qwen3 32B runs in the background. Manus starts the run, checks on it and gives you the text, json when it's ready.

**What is Qwen3 32B good at?**

Qwen3 32B is useful for code generation, math, translation, and conversations that require following detailed instructions. Use thinking for problems with several dependent steps and non-thinking for straightforward text work.

**When should I request thinking?**

Request thinking for debugging, mathematical reasoning, or comparing solutions against several constraints. For routine translation or rewriting, request a direct answer; /think and /no_think express these preferences when thinking is enabled.

**How much context can Qwen3 32B handle?**

Qwen documents 32,768 tokens natively and 131,072 tokens with YaRN context extension. The larger figure requires that extension; it is not the native context length.

**Can Qwen3 32B translate between languages?**

Yes. Qwen documents translation and multilingual instruction following, with support across 119 languages and dialects. Specify the target language, audience, and terms to preserve.

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

For thinking, Qwen recommends temperature 0.6 and top-p 0.95; for non-thinking, it recommends temperature 0.7 and top-p 0.8. Both use top-k 20 and min-p 0.

