[Integrations](https://spiral.ai/integrations) › [Amp](https://spiral.ai/integrations/amp) › [Qwen3 Coder 30B A3B Instruct](https://spiral.ai/integrations/amp/qwen3-coder-30b-a3b-instruct)

# How to Use Qwen3 Coder 30B A3B Instruct in Amp

Qwen3 Coder 30B A3B Instruct is built for coding tasks that need tool use and large code context. It supports a native 256K-token context and produces answers without a separate thinking mode.

|  |  |
| --- | --- |
| Model | Qwen3 Coder 30B A3B Instruct |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.78 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3 Coder 30B A3B Instruct in Amp

- Use Qwen3 Coder 30B A3B Instruct to investigate this project's failing tests. Reproduce the first failure, inspect the relevant implementation and callers, make the smallest fix, and report the checks you ran.
- Use Qwen3 Coder 30B A3B Instruct to trace the login flow through this repository. Identify the entry point, validation, session creation, and error handling, citing file paths and function names.
- Use Qwen3 Coder 30B A3B Instruct to complete unfinished functions in this project's parser module. Read the surrounding code and tests first, preserve the public interface, and verify each completion.
- Use Qwen3 Coder 30B A3B Instruct to add regression tests for pagination. Inspect this project's conventions and cover an empty result, the final page, and an invalid page number.
- Use Qwen3 Coder 30B A3B Instruct to refactor duplicated validation in this repository. Start with temperature 0.7, top_p 0.8, and top_k 20; preserve behavior and run the relevant tests.

## How to set up Qwen3 Coder 30B A3B Instruct 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 Coder 30B A3B Instruct**: 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-coder-30b-a3b-instruct",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## Qwen3 Coder 30B A3B Instruct tools and prices

- [Qwen: Qwen3 Coder 30B A3B Instruct](https://spiral.ai/tools/openrouter/qwen/qwen3-coder-30b-a3b-instruct) (OpenRouter): Up to $0.085882 per run at the default inputs. $0.091 per 1M input tokens, $0.364 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 235929 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Qwen3 Coder 30B A3B Instruct in Amp?

Turn a bug report into a patch checked against the project's tests with Qwen3 Coder. Give the agent the relevant code and have it use test feedback to revise the change.

### Fix a reproducible bug

Give Qwen3 Coder the failing behavior, relevant code, and test output. Request a minimal patch and a regression test that demonstrates the fix.

### Explain a request across an application

Provide the route handler, service logic, and database calls. Ask Qwen3 Coder to trace the request and identify where validation and error handling occur.

### Fill a missing implementation

Supply the code before and after an unfinished section. Ask Qwen3 Coder to complete the gap while preserving the existing interface.

### Draft tests for edge cases

Share a function and its expected behavior. Request tests for empty inputs, boundary values, and failure paths, with an explanation of each assertion.

### Refactor repeated code

Give Qwen3 Coder the repeated implementations and their callers. Request a shared implementation that preserves existing behavior, followed by targeted verification.

### Build a browser prototype

Describe a small interactive tool, its inputs, and its expected behavior. Ask Qwen3 Coder for HTML, CSS, and JavaScript plus a checklist for testing the interactions.

### Work through automated test failures

Pass test results back to Qwen3 Coder after each attempt. Ask it to revise the proposed fix and distinguish confirmed results from untested assumptions.

## Overview

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

## Qwen3 Coder 30B A3B Instruct in other agents

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

## More Amp guides

- [Qwen3 32B](https://spiral.ai/integrations/amp/qwen3-32b)
- [Qwen3 Coder 480B A35B](https://spiral.ai/integrations/amp/qwen3-coder-480b-a35b)
- [Qwen3 30B A3B Instruct 2507](https://spiral.ai/integrations/amp/qwen3-30b-a3b-instruct-2507)
- [Qwen3 Coder Flash](https://spiral.ai/integrations/amp/qwen3-coder-flash)
- [Qwen3 30B A3B](https://spiral.ai/integrations/amp/qwen3-30b-a3b)
- [Qwen3 Coder Next](https://spiral.ai/integrations/amp/qwen3-coder-next)

## Questions about Qwen3 Coder 30B A3B Instruct in Amp

**Can Amp use Qwen3 Coder 30B A3B Instruct?**

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

**How much does Qwen3 Coder 30B A3B Instruct cost in Amp?**

Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.78 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 Coder 30B A3B Instruct in Amp?**

No. Spiral runs Qwen3 Coder 30B A3B Instruct 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 Coder 30B A3B Instruct in Amp?**

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

**Does Amp wait while Qwen3 Coder 30B A3B Instruct runs?**

Qwen3 Coder 30B A3B Instruct runs in the background. Amp starts the run, checks on it and gives you the text, json when it's ready.

**What is Qwen3 Coder 30B A3B Instruct good for?**

Coding tasks that involve inspecting code, making changes, and working through tool feedback are a good fit. Try it for bug fixes, test generation, code completion, and explanations that need context from several parts of an application.

**How much code context can it handle?**

Qwen documents a native context of 256K tokens and emphasizes understanding large codebases. For a focused fix, start with the relevant implementation, callers, and tests.

**Does it have a thinking mode?**

Qwen3 Coder 30B A3B Instruct supports only non-thinking mode. Ask for a concise explanation, assumptions, and verification results when you need to assess a proposed change.

**Which programming languages does it support?**

Qwen lists 358 coding languages, including Python, JavaScript, TypeScript, Go, Rust, and SQL. Specify the language version, framework, and dependencies in your request.

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

Qwen recommends temperature 0.7, top-p 0.8, and top-k 20. Its suggested output budget is 65,536 tokens; treat that as guidance for allowing complete answers rather than a required response length or a hard ceiling.

