[Integrations](https://spiral.ai/integrations) › [Amp](https://spiral.ai/integrations/amp) › [Qwen3.6 Plus](https://spiral.ai/integrations/amp/qwen3-6-plus)

# How to Use Qwen3.6 Plus in Amp

Qwen3.6 Plus suits code changes, front-end development, and document text extraction. Its 1 million token context window supports large inputs, with text responses up to 65,536 tokens.

|  |  |
| --- | --- |
| Model | Qwen3.6 Plus |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.010399 per run at the default inputs. $0.4225 per 1M input tokens, $2.535 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3.6 Plus in Amp

- Use Qwen3.6 Plus to inspect the failing test and related source, fix the cause, and run the regression check.
- Use Qwen3.6 Plus to build a searchable settings screen using this project's components, including loading, empty, and error states.
- Use Qwen3.6 Plus to compare the implementation with the README requirements and list missing behavior with file references.
- Use Qwen3.6 Plus to reproduce the supplied screenshot in this project's front end. Label uncertain measurements.
- Use Qwen3.6 Plus with thinking enabled to plan this refactor, preserve public behavior, and propose checks before editing.

## How to set up Qwen3.6 Plus in Amp

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

### Use Spiral's MCP server

1. **Add the server**: No header and no client ID or secret: Amp registers itself with Spiral.

```bash
amp mcp add spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `amp`. Amp opens Spiral's sign-in page in your browser: sign in, pick the organization and click Authorize. No API key.

3. **Check it**

```bash
amp mcp doctor
```

### Use the Spiral skill

1. **Send Amp 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 Qwen3.6 Plus**: 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/qwen3.6-plus",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Amp finds Qwen3.6 Plus on Spiral, shows the price and runs it.

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

## Qwen3.6 Plus tools and prices

- [Qwen: Qwen3.6 Plus](https://spiral.ai/tools/openrouter/qwen/qwen3.6-plus) (OpenRouter): Up to $0.010399 per run at the default inputs. $0.4225 per 1M input tokens, $2.535 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 Qwen3.6 Plus in Amp?

Turn requirements into code changes and front-end components with Qwen3.6 Plus. Supply the relevant project files and ask for a patch with concrete acceptance checks.

### Fix a bug across related code

Give Qwen3.6 Plus the failing behavior and relevant code. Request a patch and a regression check.

### Implement a front-end screen

Describe the layout, interactions, and acceptance criteria. Ask for the component code and its empty and error states.

### Turn a screenshot into interface code

Supply a reference screenshot and ask for matching markup and styles, with uncertain dimensions labeled.

### Extract text from document images

Read document screenshots into labeled records. Request exact transcription and explicit markers for unreadable text.

### Compare lengthy specifications

Supply both specifications and request a table of changed requirements with supporting passages.

### Prepare an implementation review

Compare code with its requirements. Ask for missing behavior, affected functions, and concrete checks.

### Convert supplied text into records

Define a JSON format and provide a completed example. Extract matching records while leaving unsupported values empty.

## Overview

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

## Qwen3.6 Plus in other agents

- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-6-plus)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-6-plus)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-6-plus)
- [Cline](https://spiral.ai/integrations/cline/qwen3-6-plus)
- [Codex](https://spiral.ai/integrations/codex/qwen3-6-plus)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-6-plus)
- [Devin](https://spiral.ai/integrations/devin/qwen3-6-plus)
- [dots](https://spiral.ai/integrations/dots/qwen3-6-plus)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-6-plus)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-6-plus)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-6-plus)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-6-plus)
- [goose](https://spiral.ai/integrations/goose/qwen3-6-plus)
- [Grok](https://spiral.ai/integrations/grok/qwen3-6-plus)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-6-plus)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-6-plus)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-6-plus)
- [Manus](https://spiral.ai/integrations/manus/qwen3-6-plus)
- [Muse](https://spiral.ai/integrations/muse/qwen3-6-plus)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen3-6-plus)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-6-plus)
- [Notion](https://spiral.ai/integrations/notion/qwen3-6-plus)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-6-plus)
- [opencode](https://spiral.ai/integrations/opencode/qwen3-6-plus)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-6-plus)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-6-plus)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-6-plus)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-6-plus)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-6-plus)

## More Amp guides

- [Qwen3.6 Flash](https://spiral.ai/integrations/amp/qwen3-6-flash)
- [Qwen3.7 Flash](https://spiral.ai/integrations/amp/qwen3-7-flash)
- [Qwen3.6 35B A3B](https://spiral.ai/integrations/amp/qwen3-6-35b-a3b)
- [Qwen3.7 Max](https://spiral.ai/integrations/amp/qwen3-7-max)
- [Qwen3.6 27B](https://spiral.ai/integrations/amp/qwen3-6-27b)
- [Qwen3.7 Plus](https://spiral.ai/integrations/amp/qwen3-7-plus)

## Questions about Qwen3.6 Plus in Amp

**Can Amp use Qwen3.6 Plus?**

Yes. Add Spiral to Amp as an MCP server, and Amp can find and run Qwen3.6 Plus like any built-in tool.

**How much does Qwen3.6 Plus cost in Amp?**

Up to $0.010399 per run at the default inputs. $0.4225 per 1M input tokens, $2.535 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Amp plan is separate.

**Do I need an OpenRouter account to use Qwen3.6 Plus in Amp?**

No. Spiral runs Qwen3.6 Plus on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Qwen3.6 Plus in Amp?**

About two minutes: add the server, then sign in, then check it.

**Does Amp wait while Qwen3.6 Plus runs?**

Qwen3.6 Plus runs in the background. Amp starts the run, checks on it and gives you the text, json when it's ready.

**What is Qwen3.6 Plus good at?**

Its documented strengths include coding, front-end development, and reading text from images. Try it for code changes, interface implementation, or extracting information from document screenshots.

**How much context can Qwen3.6 Plus handle?**

The context window is 1 million tokens. That is separate from the response limit: one answer can contain up to 65,536 tokens.

**Can Qwen3.6 Plus create images or videos?**

Its output is text. It can interpret images and video, then return descriptions, extracted text, or code.

**Does Qwen3.6 Plus support a thinking mode?**

Yes, it supports both thinking and direct responses. Use thinking for tasks that require checking several constraints; request a direct response for straightforward extraction.

**How should I adjust temperature?**

Lower temperature favors more deterministic wording; higher temperature gives more varied text. Start lower for extraction and try higher values when you want several different approaches.

