How to Use Qwen3 VL 30B A3B Instruct in Claude Code
Use Qwen3 VL 30B A3B Instruct to read document images, answer visual questions, and turn screenshots into code. It provides direct responses, while Qwen3 VL 30B A3B Thinking is designed for extended reasoning.
Prompts to try with Qwen3 VL 30B A3B Instruct in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Qwen3 VL 30B A3B Instruct to turn the design screenshot in this project into HTML. Preserve its labels and layout, and save the draft for review.
Use Qwen3 VL 30B A3B Instruct to recreate the chart image in this repository with Python plotting code. Preserve axis titles and units; label estimated values.
Use Qwen3 VL 30B A3B Instruct to transcribe the scanned form in this project's fixtures. Save the text in reading order and mark unreadable characters.
Use Qwen3 VL 30B A3B Instruct to read the diagram in the project docs and explain the objects' relative positions. Cite visible labels for each relationship.
Use Qwen3 VL 30B A3B Instruct to answer which pages in this project's report images describe retention requirements. Return page references and supporting passages.
How to set up Qwen3 VL 30B A3B Instruct 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 VL 30B A3B Instruct
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-vl-30b-a3b-instruct", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds Qwen3 VL 30B A3B Instruct on Spiral, shows the price and runs it.
Qwen3 VL 30B A3B Instruct providers and prices
Spiral runs Qwen3 VL 30B A3B Instruct through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.003202 per run at the default inputs. $0.195 per 1M input tokens, $0.78 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 | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 16384 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Qwen: Qwen3 VL 30B A3B Instruct is on its tool page: open its card above.
What can you do with Qwen3 VL 30B A3B Instruct in Claude Code?
Turn screenshots and chart images into code you can edit in your project. Specify the target files and ask for a review of the generated result.
Turn a design screenshot into HTML
Generate an editable HTML draft from a screenshot or sketch. Specify which spacing, labels, and layout details to preserve.
Rebuild a chart in code
Produce plotting code from a chart image. Ask for axis labels and units, and distinguish printed values from visual estimates.
Transcribe photographed documents
Read invoice, receipt, or form images into reviewable text. Preserve line order and mark unreadable characters.
Read multilingual signs and labels
Transcribe visible wording from signs or packaging. Keep the original script and separate uncertain readings.
Find answers across document pages
Ask focused questions about a long report supplied as page images. Request page references beside each supporting passage.
Describe a scene's layout
Explain where objects sit relative to one another in a photograph. Request observable relationships and separate them from assumptions.
Index events in a demonstration
Turn timestamped video frames into a sequence of visible actions. Request start and end times with a short description of each event.
More on Qwen3 VL 30B A3B Instruct and Claude Code
Overview
Qwen3 VL 30B A3B Instruct in other agents
Questions about Qwen3 VL 30B A3B Instruct in Claude Code
Can Claude Code use Qwen3 VL 30B A3B Instruct?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Qwen3 VL 30B A3B Instruct like any built-in tool.
How much does Qwen3 VL 30B A3B Instruct cost in Claude Code?
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 Claude Code plan is separate.
Do I need an OpenRouter account to use Qwen3 VL 30B A3B Instruct in Claude Code?
No. Spiral runs Qwen3 VL 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 VL 30B A3B Instruct in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Qwen3 VL 30B A3B Instruct runs?
Qwen3 VL 30B A3B Instruct runs in the background. Claude Code starts the run, checks on it and gives you the text, json when it's ready.
Can Qwen3 VL turn a screenshot into code?
Yes. Qwen demonstrates screenshot-to-HTML generation and chart-to-plotting-code tasks. Specify the target language and which visual details the result should preserve.
How many languages can Qwen3 VL read in images?
The model card lists OCR support for 32 languages. For transcription, request the original text and mark uncertain characters separately.
How much context does Qwen3 VL support?
Qwen documents a native 256K-token context window. For long-document questions, request page references and supporting passages so you can check the answer.
How does Qwen3 VL Instruct differ from Thinking?
Instruct provides direct responses. Thinking is designed for extended reasoning; these are separately trained models.
Where should I check Qwen3 VL's visual answers carefully?
Check answers that depend on tiny labels or subtle visual distinctions. Qwen reports substantial benefits from external tools on fine-detail tasks; supply a close-up and ask for visible evidence.
Start using Qwen3 VL 30B A3B Instruct 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


