How to Use Schematron V2 Small in Notion
Schematron V2 Small turns HTML into typed JSON, with particular strength on complex schemas and long pages. Choose it when extraction quality matters most; Schematron V2 Turbo prioritizes throughput.
Prompts to try with Schematron V2 Small in Notion
Copy an example into Notion, or ask in your own words.
Each morning, fetch my tracked product pages and use Schematron V2 Small to extract availability. Compare records with yesterday and list changes.
Every weekday, fetch the tracked careers pages and use Schematron V2 Small to extract roles and locations. Report newly observed postings.
Each evening, fetch the tracked publication pages. Use Schematron V2 Small with an article schema to extract headlines, authors, dates, and links.
Weekly, fetch my tracked company pages and extract names, descriptions, and contact details with Schematron V2 Small. Flag changes for review.
Daily, fetch tracked product pages and use Schematron V2 Small to extract specifications. Process sections separately so each JSON result stays below 4K tokens.
How to set up Schematron V2 Small in Notion
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Notion 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
- Allow custom MCP servers
A workspace owner opens Settings › Connections, then the Manage tab, and turns on Enable custom MCP servers. Where members may install only approved connections, also add Spiral under Approved connections › Add approved connection › Custom MCP server with the URL below.
- Add Spiral to a custom agent
Open the custom agent (or create one), then Settings › Tools & Access › Add connection › Custom MCP server. Paste this URL, name it Spiral, keep OAuth and click Connect.
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Notion never sees it, and you can remove it under Settings › Connected apps in the console.
- Run Schematron V2 Small in a workflow step
Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Schematron V2 Small, prices it and runs it each time the step fires.
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 Schematron V2 Small
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": "inference-net/schematron-v2-small", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Notion finds Schematron V2 Small on Spiral, shows the price and runs it.
Schematron V2 Small providers and prices
Spiral runs Schematron V2 Small through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.001228 per run at the default inputs. $0.065 per 1M input tokens, $0.299 per 1M output tokens.
Settings you can ask for
Ask Notion 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 | ||
| Max tokens | 1 to 8192 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Inference.net: Schematron V2 Small is on its tool page: open its card above.
What can you do with Schematron V2 Small in Notion?
Keep structured records current as tracked webpages change. A scheduled agent can fetch the HTML, run schema-guided extraction, and compare each result with its previous observation.
Product catalog ingestion
Extract product names, current sale prices, specifications, and availability from product-page HTML into consistent records.
Job posting collection
Turn job-page HTML into records containing employer, role, location, requirements, and advertised compensation. Allow missing compensation to remain null.
Article metadata indexing
Extract headlines, authors, publication dates, and article links from supplied HTML for a searchable content index.
Company directory enrichment
Convert company-page HTML into records of names, descriptions, locations, and contact details explicitly present on each page.
Recurring product monitoring
Have an agent fetch tracked pages, extract current product details, and compare the resulting records with earlier observations.
Parser replacement evaluation
Run extraction against saved HTML alongside an existing parser. Compare individual fields before replacing parsing rules.
More on Schematron V2 Small and Notion
Overview
Schematron V2 Small in other agents
Questions about Schematron V2 Small in Notion
Can Notion use Schematron V2 Small?
Yes. Add Spiral to Notion as an MCP server, and Notion can find and run Schematron V2 Small like any built-in tool.
How much does Schematron V2 Small cost in Notion?
Up to $0.001228 per run at the default inputs. $0.065 per 1M input tokens, $0.299 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Notion plan is separate.
Do I need an OpenRouter account to use Schematron V2 Small in Notion?
No. Spiral runs Schematron V2 Small on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Schematron V2 Small in Notion?
About two minutes: allow custom MCP servers, then add Spiral to a custom agent, then sign in to Spiral and approve.
Does Notion wait while Schematron V2 Small runs?
Schematron V2 Small runs in the background. Notion starts the run, checks on it and gives you the text, json when it's ready.
What is Schematron V2 Small best used for?
Extracting typed records from HTML, especially when pages are long or the desired schema is complex. Product catalogs, job postings, and article metadata are useful starting points.
How should I write extraction instructions?
Put the instructions into schema descriptions. Specify which value to extract when several appear, such as the current sale price versus the original price; conversational directions do not steer extraction.
Can Schematron V2 Small open a webpage itself?
It needs HTML supplied by your agent or crawler. It does not fetch web addresses or render JavaScript, so your agent must obtain the page content before extraction.
How much HTML and JSON can it handle?
The maker lists a 128K-token context window and a 4K-token maximum output. Split large extraction jobs into smaller sections when the requested JSON would exceed that output allowance.
What improves extraction accuracy?
Use temperature zero, remove scripts and styles, and keep the HTML that contains the desired information. Add precise schema descriptions wherever multiple values could fit the same field.
Start using Schematron V2 Small in Notion
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Notion:
set up https://spiral.ai/SKILL.md


