How to Use Perceptron Mk1.5 in Devin
Perceptron Mk1.5 turns images and recordings into descriptions, extracted text, and spatial or timed annotations. Compared with Perceptron Mk1, it adds native audio support and video object tracking.
Prompts to try with Perceptron Mk1.5 in Devin
Copy an example into Devin, or ask in your own words.
Use Perceptron Mk1.5 to transcribe the scanned pages in this project's test assets into Markdown. Preserve reading order and mark unreadable spans.
Use Perceptron Mk1.5 to count visible cartons in the project's warehouse photo. List the evidence for each count and exclude pallets.
Use Perceptron Mk1.5 to find every door-opening event in the project's sample video. Produce separate start and end times in seconds.
Use Perceptron Mk1.5 to analyze the project's basketball clip. Track only visible ball positions with timestamps, leaving gaps during occlusion.
Use Perceptron Mk1.5 to draft captions for this project's image assets. Describe visible objects and layout without inferring intentions.
How to set up Perceptron Mk1.5 in Devin
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add a custom MCP
Open Customize › MCPs. Click + and choose New MCP. Fill in:
- Sign in to Spiral and approve
In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.
- Check it
On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.
Use the Spiral skill
- Send Devin 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 Perceptron Mk1.5
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": "perceptron/perceptron-mk1.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Devin finds Perceptron Mk1.5 on Spiral, shows the price and runs it.
Perceptron Mk1.5 providers and prices
Spiral runs Perceptron Mk1.5 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.007995 per run at the default inputs. $0.195 per 1M input tokens, $1.95 per 1M output tokens.
Settings you can ask for
Ask Devin for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 8192 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Reasoning effort | none, minimal, low, medium, or high | high | How much the model reasons. |
| Frequency penalty | -2 to 2 |
Every API field of Perceptron: Perceptron Mk1.5 is on its tool page: open its card above.
What can you do with Perceptron Mk1.5 in Devin?
Turn project images and recordings into reviewable text, counts, and event timelines. Use Perceptron Mk1.5 to draft evidence that your code can validate and display.
Turn document images into editable text
Transcribe scanned pages in reading order, preserving headings and tables. Mark unreadable text instead of filling it in.
Count visible inventory
Count a named object category in a shelf photo. Define exclusions and request a location for each counted object so the result can be reviewed.
Find repeated actions in video
Locate each door opening or other clearly described event. Return separate start and end times for review.
Review a ball's movement
Follow a clearly identified ball through a sports clip. Request observed positions with timestamps and leave gaps when it disappears.
Describe image collections
Draft captions covering visible objects, their arrangement, and the setting. Keep uncertain interpretations separate from observations.
Summarize recorded discussions
Extract stated decisions and unresolved questions from short recordings. Flag unclear speech rather than inventing missing words.
More on Perceptron Mk1.5 and Devin
Overview
Perceptron Mk1.5 in other agents
Questions about Perceptron Mk1.5 in Devin
Can Devin use Perceptron Mk1.5?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Perceptron Mk1.5 like any built-in tool.
How much does Perceptron Mk1.5 cost in Devin?
Up to $0.007995 per run at the default inputs. $0.195 per 1M input tokens, $1.95 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Devin plan is separate.
Do I need an OpenRouter account to use Perceptron Mk1.5 in Devin?
No. Spiral runs Perceptron Mk1.5 on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Perceptron Mk1.5 in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Does Devin wait while Perceptron Mk1.5 runs?
Perceptron Mk1.5 runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.
What is Perceptron Mk1.5 useful for?
Use it to inspect visual evidence: read text in images, count visible objects, locate events in video, and follow an object over time. It also summarizes recordings and transcribes speech.
Does Perceptron Mk1.5 generate audio?
It analyzes recordings and returns text. It does not generate audio.
How much content can Perceptron Mk1.5 handle?
The context window is 36,864 tokens, with up to 8,192 completion tokens. Audio also has a separate cap of 16,384 audio tokens per recording, approximately 21.8 minutes; split longer recordings.
Can Perceptron Mk1.5 track an object through every video frame?
It returns timestamped observations that may be sparse. Treat gaps as missing evidence, especially when the object is hidden or off-screen.
Does valid JSON mean the extracted information is correct?
No. A schema controls the answer's structure, but the model can still misread the image or interpret it incorrectly. Check extracted values against the source.
Start using Perceptron Mk1.5 in Devin
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Devin:
set up https://spiral.ai/SKILL.md


