How to Use Qwen2.5-VL 72B Instruct in Perplexity
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 Perplexity
Copy an example into Perplexity, or ask in your own words.
Use Qwen2.5-VL 72B Instruct to read this invoice image. Give me a table of line items and the printed total, and mark anything unreadable.
Use Qwen2.5-VL 72B Instruct to explain this chart. Read the axes and legend first, then describe the main comparison using only visible evidence.
Use Qwen2.5-VL 72B Instruct to compare these screenshots, labeled Image A and Image B. List changes to visible text and layout.
Use Qwen2.5-VL 72B Instruct to transcribe this Japanese sign. Preserve the original script and line breaks, and mark uncertain characters.
Use Qwen2.5-VL 72B Instruct to count the cups in this image. Locate each cup first, then give the total and flag any ambiguous objects.
How to set up Qwen2.5-VL 72B Instruct in Perplexity
Pick the way that suits you. Each takes about two minutes.
Use the Perplexity connector
- Add a remote connector
In Perplexity, open Plugins in the sidebar (or Customize › Connectors if you don't see Plugins yet). Choose Add custom › Add MCP connector, then Remote. Name it Spiral and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Select the Spiral card on the Plugins page to start sign-in. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Perplexity 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 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: Perplexity 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 Perplexity 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 Perplexity?
Read charts, scans, and screenshots with Qwen2.5-VL to answer questions about what is visible. Request a table, an explanation, or labeled object locations according to the task.
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 Perplexity
Overview
Qwen2.5-VL 72B Instruct in other agents
Questions about Qwen2.5-VL 72B Instruct in Perplexity
Can Perplexity use Qwen2.5-VL 72B Instruct?
Yes. Add Spiral to Perplexity as an MCP server, and Perplexity can find and run Qwen2.5-VL 72B Instruct like any built-in tool.
How much does Qwen2.5-VL 72B Instruct cost in Perplexity?
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 Perplexity plan is separate.
Do I need an OpenRouter account to use Qwen2.5-VL 72B Instruct in Perplexity?
No. Spiral runs Qwen2.5-VL 72B 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 Qwen2.5-VL 72B Instruct in Perplexity?
About two minutes: add a remote connector, then sign in to Spiral and approve.
Does Perplexity wait while Qwen2.5-VL 72B Instruct runs?
Qwen2.5-VL 72B Instruct runs in the background. Perplexity 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 Perplexity
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Perplexity:
set up https://spiral.ai/SKILL.md


