[Integrations](https://spiral.ai/integrations) › [Windsurf](https://spiral.ai/integrations/windsurf) › [Qwen3 Coder Next](https://spiral.ai/integrations/windsurf/qwen3-coder-next)

# How to Use Qwen3 Coder Next in Windsurf

Qwen3 Coder Next is built for coding tasks that involve reading code, using tools, and fixing execution failures. It pairs a native 262,144-token context window with non-thinking output for repository work.

|  |  |
| --- | --- |
| Model | Qwen3 Coder Next |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.004266 per run at the default inputs. $0.156 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 Coder Next in Windsurf

- Use Qwen3 Coder Next to investigate this project's failing tests. Run the relevant suite, trace the first failure to its cause, make a focused fix, and report the checks you ran.
- Use Qwen3 Coder Next to trace this project's login flow across the relevant files. Find why an expired session returns a server error, add a regression test, and patch the behavior without changing the public API.
- Use Qwen3 Coder Next to refactor duplicated validation in this repository into a shared function. Preserve existing error messages and call signatures, then run the affected tests.
- Use Qwen3 Coder Next to finish the incomplete CSV parser in this project. Follow the surrounding code's conventions and test quoted commas, escaped quotes, empty cells, and malformed rows.
- Use Qwen3 Coder Next to implement the missing empty and error states in this project's search page. Run the app, exercise each state, and report any rendering or interaction problems that remain.

## How to set up Qwen3 Coder Next in Windsurf

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

### Use Spiral's MCP server

1. **Add the server**: Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: `~/.config/devin/mcp_config.json` on macOS and Linux, `%APPDATA%\devin\mcp_config.json` on Windows. Add this:

```json
{
  "mcpServers": {
    "spiral": {
      "url": "https://api.spiral.ai/mcp"
    }
  }
}
```

2. **Sign in**: Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.

```bash
devin mcp login spiral
```

3. **Check it**: Spiral is listed under This computer in Customize › MCPs. From the terminal:

```bash
devin mcp list
```

### Use the Spiral skill

1. **Send Windsurf 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 Next**: 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-next",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Windsurf finds Qwen3 Coder Next on Spiral, shows the price and runs it.

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

## Qwen3 Coder Next tools and prices

- [Qwen: Qwen3 Coder Next](https://spiral.ai/tools/openrouter/qwen/qwen3-coder-next) (OpenRouter): Up to $0.004266 per run at the default inputs. $0.156 per 1M input tokens, $1.04 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 Coder Next in Windsurf?

Turn a repository issue into an inspected, edited, and tested patch with Qwen3 Coder Next. Give the agent a reproduction command and acceptance criteria so it can use execution feedback to revise its work.

### Fix a repository bug

Ask Qwen3 Coder Next to trace a reported failure across relevant code, make a focused patch, and verify the behavior with a regression test.

### Investigate failing tests

Give Qwen3 Coder Next the failure output and relevant implementation. Ask it to distinguish an implementation defect from an incorrect test expectation before proposing changes.

### Refactor code across languages

Use Qwen3 Coder Next for focused code edits with explicit compatibility requirements. Ask for a patch and checks that show the intended behavior still holds.

### Diagnose command failures

Provide Qwen3 Coder Next with the command, error output, and environment details. Ask for the next diagnostic action and a revised approach after each result.

### Draft SQL from a schema

Give Qwen3 Coder Next table definitions, join relationships, and a reporting question. Request a query with explicit treatment of duplicates, missing values, and date boundaries.

### Build a small web application

Ask Qwen3 Coder Next to implement a defined workflow, including validation and error states. Review the rendered interface closely because Qwen identifies UI work as a weakness.

### Complete a missing code section

Show Qwen3 Coder Next the surrounding code and describe the missing behavior. Request a replacement that preserves the existing interface and includes example checks.

## Overview

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

## Qwen3 Coder Next in other agents

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

## More Windsurf guides

- [Qwen3 Coder Flash](https://spiral.ai/integrations/windsurf/qwen3-coder-flash)
- [Qwen3 Next 80B A3B Instruct](https://spiral.ai/integrations/windsurf/qwen3-next-80b-a3b-instruct)
- [Qwen3 Coder 480B A35B](https://spiral.ai/integrations/windsurf/qwen3-coder-480b-a35b)
- [Qwen3 VL 235B A22B Instruct](https://spiral.ai/integrations/windsurf/qwen3-vl-235b-a22b-instruct)
- [Qwen3 Coder 30B A3B Instruct](https://spiral.ai/integrations/windsurf/qwen3-coder-30b-a3b-instruct)
- [Qwen3 VL 30B A3B Instruct](https://spiral.ai/integrations/windsurf/qwen3-vl-30b-a3b-instruct)

## Questions about Qwen3 Coder Next in Windsurf

**Can Windsurf use Qwen3 Coder Next?**

Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run Qwen3 Coder Next like any built-in tool.

**How much does Qwen3 Coder Next cost in Windsurf?**

Up to $0.004266 per run at the default inputs. $0.156 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 Windsurf plan is separate.

**Do I need an OpenRouter account to use Qwen3 Coder Next in Windsurf?**

No. Spiral runs Qwen3 Coder Next 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 Next in Windsurf?**

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

**Does Windsurf wait while Qwen3 Coder Next runs?**

Qwen3 Coder Next runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.

**What is Qwen3 Coder Next best suited for?**

Use it for coding tasks that benefit from several rounds of inspection, tool use, and correction. Repository debugging is a practical example: ask it to investigate a failure, propose a patch, and check the result.

**How much context does Qwen3 Coder Next support?**

Its native context window is 262,144 tokens. For repository questions, provide the relevant implementation, dependencies, and failure evidence together.

**Does Qwen3 Coder Next have a thinking mode?**

No. Qwen documents non-thinking mode only, without separate thinking blocks in the output.

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

Start with Qwen's published settings: temperature 1.0, top-p 0.95, and top-k 40. Use these as a baseline when comparing results on your own coding tasks.

**Can Qwen3 Coder Next work across programming languages?**

Yes. Qwen documents broad programming-language support and evaluates multilingual code editing; specify the language, runtime version, and behavior you need preserved.

