How to Use Qwen4 Max in VS Code
Qwen4 Max is built for coding, office work, front-end design, and tasks that require several reasoning steps. Its one-million-token context supports analysis across long documents and large codebases.
Prompts to try with Qwen4 Max in VS Code
Copy an example into VS Code, or ask in your own words.
Use Qwen4 Max to trace the failing test through the relevant project files. Identify the cause, implement the smallest fix, and run a regression test that fails before the fix.
Use Qwen4 Max to review the authentication code and its callers. Return up to five concrete defects with file references, a reproduction path, and a proposed correction.
Use Qwen4 Max to implement the settings screen described in the project's requirements. Cover loading, empty, error, and saved states, and verify keyboard navigation.
Use Qwen4 Max to compare the current data layer with the migration proposal. Map affected files and dependencies, then produce an ordered plan with a check for each stage.
Use Qwen4 Max to examine the ticket parser and its tests. Propose a consistent JSON contract, then add coverage for missing values, malformed input, and unexpected extra text.
How to set up Qwen4 Max in VS Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to VS Code on the console's Agents & MCP page, or run:
code --add-mcp '{"name":"spiral","type":"http","url":"https://api.spiral.ai/mcp"}' - Sign in
VS Code asks you to sign in when it first starts the server: sign in to Spiral and click Authorize. No API key. Run MCP: List Servers from the Command Palette to check that Spiral is running.
Use the Spiral skill
- Send VS Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Qwen4 Max
One request; the result comes back by polling or a webhook.
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/qwen4-max", "input": { "messages": [ { "role": "user", "content": "Hello!" } ] } }'
Then paste one of the prompts above: VS Code finds Qwen4 Max on Spiral, shows the price and runs it.
Qwen4 Max providers and prices
Spiral runs Qwen4 Max through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.02283 per run at the default inputs. $1.8525 per 1M input tokens, $5.5575 per 1M output tokens.
Settings you can ask for
Ask VS Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 131072 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | none, low, high, or xhigh | high | How much the model reasons. |
| Frequency penalty | -2 to 2 |
Every API field of Qwen: Qwen4 Max is on its tool page: open its card above.
What can you do with Qwen4 Max in VS Code?
Turn changes spanning several modules into an implementation plan, patch, and focused checks with Qwen4 Max. Its long context and coding focus suit work that requires following relationships across project files.
Trace a bug across modules
Ask Qwen4 Max to follow a failing request through related code, identify the cause, and propose a focused fix with a regression test.
Plan a codebase migration
Have Qwen4 Max compare existing interfaces with the target design and produce an ordered migration plan with dependencies and acceptance checks.
Build a front end from requirements
Give Qwen4 Max a written interface brief covering content, interactions, accessibility, and screen sizes, then request the implementation.
Compare lengthy specifications
Use Qwen4 Max to compare supplied specifications, identify conflicting requirements, and cite the relevant sections in a decision table.
Extract support ticket details
Ask Qwen4 Max to turn ticket text into JSON with a defined set of keys, using null for missing details and examples to establish the format.
Prepare an operational brief
Have Qwen4 Max combine supplied updates into a concise brief covering decisions, owners, deadlines, and unresolved questions.
Analyze a multi-step decision
Ask Qwen4 Max to compare options against supplied constraints, work through dependencies, and explain the evidence behind a recommendation.
More on Qwen4 Max and VS Code
Overview
Qwen4 Max in other agents
Questions about Qwen4 Max in VS Code
Can VS Code use Qwen4 Max?
Yes. Add Spiral to VS Code as an MCP server, and VS Code can find and run Qwen4 Max like any built-in tool.
How much does Qwen4 Max cost in VS Code?
Up to $0.02283 per run at the default inputs. $1.8525 per 1M input tokens, $5.5575 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your VS Code plan is separate.
Do I need an OpenRouter account to use Qwen4 Max in VS Code?
No. Spiral runs Qwen4 Max on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen4 Max in VS Code?
About two minutes: add the hosted server, then sign in.
Does VS Code wait while Qwen4 Max runs?
Qwen4 Max runs in the background. VS Code starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen4 Max good at?
Qwen4 Max is designed for coding, office work, front-end design, and complex agent tasks. Useful requests include tracing a bug across several modules or turning detailed requirements into an implementation plan.
How much context can Qwen4 Max handle?
The maker documents a one-million-token context window. That makes long document comparisons and analysis across large codebases practical uses.
How long can Qwen4 Max's answers be?
The maker lists up to 131,072 output tokens without thinking. Its documented thinking-mode limit is 262,144 tokens shared between reasoning and the final answer, so that number does not describe answer length alone.
When is deeper thinking useful?
Use it for tasks that require choosing tools, interpreting results, and deciding what to do next. The maker cautions that the overhead may not be worthwhile for a simple task involving one tool.
Does valid JSON guarantee consistent output?
No. JSON Object mode can return valid JSON while changing key names or value types; the maker recommends JSON Schema mode when the structure must stay fixed.
Start using Qwen4 Max in VS Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into VS Code:
set up https://spiral.ai/SKILL.md


