How to Use Qwen3.8 Max (0902) in Claude Code
Qwen3.8 Max (0902) is built for software projects, document analysis, and tasks that require several tools. Compared with Qwen3.8 Max, it adds post-training focused on coding, tool orchestration, and visual understanding.
Prompts to try with Qwen3.8 Max (0902) in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Qwen3.8 Max (0902) to trace this project's failing tests, fix the underlying bug, and report the verification results.
Use Qwen3.8 Max (0902) to inspect authentication across the project and propose a migration plan with testable checkpoints.
Use Qwen3.8 Max (0902) to compare the implementation with the project specification and list discrepancies with file references.
Use Qwen3.8 Max (0902) to review this project's document extraction code and add validation for missing keys and incorrect types.
Use Qwen3.8 Max (0902) to implement the requested feature, run relevant checks, and identify any acceptance criteria still unmet.
How to set up Qwen3.8 Max (0902) in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude 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 Qwen3.8 Max (0902)
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/qwen3.8-max-0902", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds Qwen3.8 Max (0902) on Spiral, shows the price and runs it.
Qwen3.8 Max (0902) providers and prices
Spiral runs Qwen3.8 Max (0902) through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens.
Settings you can ask for
Ask Claude 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. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | minimal, low, medium, high, or xhigh | xhigh | How much the model reasons. |
| Frequency penalty | -2 to 2 |
Every API field of Qwen: Qwen3.8 Max (0902) is on its tool page: open its card above.
What can you do with Qwen3.8 Max (0902) in Claude Code?
Qwen3.8 Max can help carry a software task from investigation through implementation and verification. Give the agent project context, acceptance criteria, and a focused test target.
Debug a feature across several files
Trace a reported failure through the relevant code, propose a fix, and check it against focused tests.
Plan a software migration
Map dependencies, divide the work into testable changes, and identify assumptions that need verification before implementation.
Compare lengthy documents
Build a table of agreements, contradictions, and missing information, with a source passage for each finding.
Explain charts
Read chart images, identify units and trends, and separate visible values from estimates.
Extract document records
Turn document content into JSON records for review. Validate keys and types, particularly when the source includes images.
Draft a research brief
Organize retrieved evidence into findings, competing explanations, and unanswered questions with source references.
Review a recorded demonstration
Analyze video for the steps shown, points of confusion, and evidence supporting a written walkthrough.
More on Qwen3.8 Max (0902) and Claude Code
Overview
Qwen3.8 Max (0902) in other agents
Questions about Qwen3.8 Max (0902) in Claude Code
Can Claude Code use Qwen3.8 Max (0902)?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Qwen3.8 Max (0902) like any built-in tool.
How much does Qwen3.8 Max (0902) cost in Claude Code?
Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need an OpenRouter account to use Qwen3.8 Max (0902) in Claude Code?
No. Spiral runs Qwen3.8 Max (0902) on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Qwen3.8 Max (0902) in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Qwen3.8 Max (0902) runs?
Qwen3.8 Max (0902) runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen3.8 Max best suited for?
Its documented focus includes software projects, research, and tasks that require several tools. Useful starting points include debugging a feature, comparing documents, and turning source material into a structured report.
How much context and output does Qwen3.8 Max support?
The maker lists a 1M-token context window and up to 131K output tokens. Treat these as ceilings, and request a specific deliverable length rather than the longest possible answer.
Does Qwen3.8 Max generate images or videos?
Its output is text, although it can analyze images and video. Ask for chart explanations, document extraction, or descriptions of visual evidence.
Can I rely on Qwen3.8 Max to return a fixed JSON structure?
The maker warns that JSON Object mode does not guarantee stable keys or types and recommends JSON Schema mode for a fixed structure. Its documentation also says multimodal inputs fall back to JSON Object mode, so validate extracted records before using them.
Why can reasoning leave less room for the final answer?
The maker's Responses API counts reasoning and answer tokens together toward the output limit. Reserve enough room for both when requesting a long report or code changes.
Start using Qwen3.8 Max (0902) in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


