How to Use Qwen3.7 Flash in Instinct
Qwen3.7 Flash suits visual coding, screenshot analysis, and agents that use tools. Compared with Qwen3.6 Flash, Qwen reports improved multimodal understanding and more stable agent execution.
Prompts to try with Qwen3.7 Flash in Instinct
Copy an example into Instinct, or ask in your own words.
Each morning, use Qwen3.7 Flash to compare the latest homepage screenshot with the approved reference. Report visible text, layout, and control changes, with a location and short description for each.
Every weekday, use Qwen3.7 Flash to review newly submitted product photos. Return JSON listing visible objects, their relative positions, and uncertain identifications for human review.
Each evening, use Qwen3.7 Flash to summarize today's retrieved browser-testing release notes. Include a source link for every reported change and omit claims the retrieved text does not support.
Every Monday, use Qwen3.7 Flash to review the latest 60-second silent product demonstration. Produce a numbered list of visible actions and compare it with the previously approved sequence.
After each scheduled screenshot capture, use Qwen3.7 Flash to inventory visible navigation controls. Return JSON with label, location, and destination when visibly stated; use null for unknown destinations.
How to set up Qwen3.7 Flash in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct 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 Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
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 Qwen3.7 Flash
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/qwen3.7-flash", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Qwen3.7 Flash on Spiral, shows the price and runs it.
Qwen3.7 Flash providers and prices
Spiral runs Qwen3.7 Flash through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.000695 per run at the default inputs. $0.039 per 1M input tokens, $0.169 per 1M output tokens.
Settings you can ask for
Ask Instinct for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 65536 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 |
Every API field of Qwen: Qwen3.7 Flash is on its tool page: open its card above.
What can you do with Qwen3.7 Flash in Instinct?
Turn recurring visual checks and retrieved evidence into consistent review reports with Qwen3.7 Flash. Define the comparison rules and output structure so each scheduled run answers the same questions.
Implement a UI from a screenshot
Ask Qwen3.7 Flash to translate a reference screenshot into interface code, with explicit requirements for layout, text, and responsive behavior.
Review visual regressions
Give Qwen3.7 Flash before-and-after screenshots and ask for a list of visible differences, including the affected region and expected appearance.
Turn interface screenshots into test plans
Use Qwen3.7 Flash to identify visible controls and draft test steps with expected results. Ask it to flag behavior that cannot be established from the screenshot.
Catalog visible objects
Ask Qwen3.7 Flash to list objects in product or workspace images, describe their relative positions, and return the results in a defined JSON structure.
Summarize a visual demonstration
Have Qwen3.7 Flash turn a demonstration clip into numbered steps based on visible actions. Supply a separate transcript if spoken instructions matter.
Draft search briefs from retrieved evidence
Use Qwen3.7 Flash to organize search results into findings, supporting links, and unresolved questions. Require a source for each finding.
Plan computer interaction tasks
Ask Qwen3.7 Flash to inspect an interface screenshot and propose the next action toward a stated goal, naming the visible control and evidence for choosing it.
More on Qwen3.7 Flash and Instinct
Overview
Qwen3.7 Flash in other agents
More Instinct guides
Questions about Qwen3.7 Flash in Instinct
Can Instinct use Qwen3.7 Flash?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Qwen3.7 Flash like any built-in tool.
How much does Qwen3.7 Flash cost in Instinct?
Up to $0.000695 per run at the default inputs. $0.039 per 1M input tokens, $0.169 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need an OpenRouter account to use Qwen3.7 Flash in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Qwen3.7 Flash on its own OpenRouter account.
How long does it take to set up Qwen3.7 Flash in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Qwen3.7 Flash runs?
Qwen3.7 Flash runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen3.7 Flash best used for?
Its documented strengths include visual coding, object recognition, spatial understanding, and tool-driven tasks. Useful starting points include reviewing screenshots, interpreting interfaces, and turning visual evidence into text.
How much context can Qwen3.7 Flash handle?
Qwen documents a one-million-token context window. Keep the task focused even when supplying substantial context: state the question, identify the relevant material, and specify the output you need.
Can Qwen3.7 Flash generate images or video?
Qwen3.7 Flash produces text from text, image, or video input. Use it to describe a scene, analyze a screenshot, or explain a clip.
Can Qwen3.7 Flash understand speech in a video?
It analyzes the visual content but does not understand the video's audio track. Supply a transcript when the task depends on spoken words; Qwen documents video durations from two seconds to two hours.
When should I use thinking with Qwen3.7 Flash?
Use thinking for tasks that require choosing several tools and interpreting their results. Qwen3.7 Flash supports switching thinking on or off, so compare both approaches on representative tasks.
Start using Qwen3.7 Flash in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


