How to Use Qwen2.5-VL 72B Instruct in Instinct
Use Qwen2.5-VL 72B Instruct to extract data from scanned documents and explain charts. It can also locate objects with bounding boxes or points, making it useful when an answer needs a position in the image.
Prompts to try with Qwen2.5-VL 72B Instruct in Instinct
Copy an example into Instinct, or ask in your own words.
Each morning, use Qwen2.5-VL 72B Instruct to read the invoice images supplied for that run. Report supplier, invoice number, date, and printed total, with a separate list of unreadable entries.
Every weekday, use Qwen2.5-VL 72B Instruct to compare the supplied dashboard screenshots, labeled Previous and Current. Report visible changes to chart labels and values.
Each evening, use Qwen2.5-VL 72B Instruct to transcribe the supplied form images into a table. Preserve printed labels and mark missing or unreadable entries.
Every Monday, use Qwen2.5-VL 72B Instruct to transcribe the supplied French and German sign images. Keep the original text and identify uncertain words for review.
For each scheduled image batch, use Qwen2.5-VL 72B Instruct to locate every visible package before counting them. Return an image label, individual locations, and a total for each image.
How to set up Qwen2.5-VL 72B Instruct 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 Qwen2.5-VL 72B 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/qwen2.5-vl-72b-instruct", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Qwen2.5-VL 72B Instruct on Spiral, shows the price and runs it.
Qwen2.5-VL 72B Instruct providers and prices
Spiral runs Qwen2.5-VL 72B Instruct through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.005362 per run at the default inputs. $1.04 per 1M input tokens, $1.30 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 k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 115200 | 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: Qwen2.5 VL 72B Instruct is on its tool page: open its card above.
What can you do with Qwen2.5-VL 72B Instruct in Instinct?
Turn recurring batches of document images and screenshots into reviewable reports with Qwen2.5-VL. A scheduled agent can request consistent extraction columns and attach visible evidence to each finding.
Invoice extraction
Turn invoice images into records containing the supplier, invoice number, date, line items, and total. Mark unreadable values for review.
Form transcription
Extract printed labels and completed entries from form images into a consistent table.
Chart explanations
Read chart titles, axes, legends, and visible values, then explain the comparison in plain English.
Screenshot review
Inspect interface screenshots for visible labels, layout differences, and the locations of named controls.
Multilingual text collection
Transcribe signs or document images in languages covered by Qwen's OCR training, preserving the original script.
Object annotation
Locate specified objects in images and return labeled bounding boxes or points for review.
Visual counting
Identify each visible instance of a requested object before returning a count and locations that a reviewer can inspect.
More on Qwen2.5-VL 72B Instruct and Instinct
Overview
Qwen2.5-VL 72B Instruct in other agents
Questions about Qwen2.5-VL 72B Instruct in Instinct
Can Instinct use Qwen2.5-VL 72B Instruct?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Qwen2.5-VL 72B Instruct like any built-in tool.
How much does Qwen2.5-VL 72B Instruct cost in Instinct?
Up to $0.005362 per run at the default inputs. $1.04 per 1M input tokens, $1.30 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 Qwen2.5-VL 72B Instruct in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Qwen2.5-VL 72B Instruct on its own OpenRouter account.
How long does it take to set up Qwen2.5-VL 72B Instruct in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Qwen2.5-VL 72B Instruct runs?
Qwen2.5-VL 72B Instruct runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Qwen2.5-VL useful for?
Use it to extract information from document images, interpret charts, and locate objects. Good starting tasks include turning an invoice scan into structured data or explaining a chart's labels and values.
Can Qwen2.5-VL extract tables and forms?
Yes. It supports structured extraction from scanned tables, forms, and invoices. Specify the columns you want and ask it to mark unreadable entries instead of guessing.
Which languages does Qwen2.5-VL's OCR training cover?
Qwen names French, German, Italian, Spanish, Portuguese, Arabic, Russian, Japanese, Korean, and Vietnamese in its multilingual OCR training data. Treat that list as training coverage, not a promise of equal accuracy across languages.
What context limit does Qwen publish?
The model card describes a default configuration of 32,768 tokens. It also warns that YaRN context extension affects spatial and temporal localization, so a longer configuration should not be assumed to preserve location accuracy.
How should I prompt Qwen2.5-VL to count objects?
Ask it to locate each object first, then report the total. Qwen uses this detect-then-count approach in its reported evaluation; check the returned locations against the image.
Start using Qwen2.5-VL 72B Instruct 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


