Can I run Schematron V2 Small locally?

Yes — the weights are open and hosted on Hugging Face under inference-net/schematron-v2-llama-3.2-3b, so you can download and run it yourself.

What does it cost and how much context does it have?

Via Inference.net the API is priced at $0.05 per million input tokens and $0.23 per million output tokens, with a 128,000-token context window.

How do I give it extraction instructions?

You do not use system or user prompts for instructions — the model expects a JSON schema supplied through the response_format parameter, and that schema defines what it extracts.

Schematron V2 Small

3712°

#llm #inference-net #data extraction #local #budget #fast

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Inference.net | 128,000 token context | $0.05/M input, $0.23/M output. Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Schematron V2 Small is a 3-billion-parameter model from Inference.net built for one job: pulling structured data out of HTML and returning it as JSON. At 3B parameters it stays lean and cheap, while the V2 generation targets extraction quality on complex schemas and long pages. If you are scraping, parsing or piping web content into a pipeline, this is purpose-built for that work.

Known for

Structured HTML-to-JSON extraction as its sole focus
Handles complex schemas and long HTML pages without degrading
128,000-token context window fits most real-world pages
Open weights available on Hugging Face for local deployment
Very low API cost: fractions of a cent per page at typical sizes

Watch out for

Instructions must go through a JSON schema in response_format — system and user prompts are not how you drive this model.
Narrow specialist: it does one thing well and is not a general-purpose assistant.
Licence terms are not published by the maker; check the Hugging Face repository before commercial use.

Best for

Prompts to try

Extract product data

Paste the raw HTML of an e-commerce product page below. Use response_format with a JSON schema that captures: product name, price, currency, availability status, bullet-point features as an array, and the first image URL. Return only the JSON object, no commentary.

Parse a news article

Here is the full HTML of a news article. Use response_format with a schema that extracts: headline, author name, publication date in ISO 8601, body text as a single string, and all hyperlinks in the body as an array of objects with anchor text and href.

Scrape a job listing

Below is the HTML of a job posting page. Use response_format with a schema that captures: job title, company name, location, salary range if present, employment type, required skills as an array, and the full job description as plain text stripped of HTML tags.

Compare with

Schematron V2 Turbo
Open-weights model
128,000 token context · $0.03/M input, $0.15/M output
Gemini 3.1 Flash Lite
API-only model
1,048,576 token context · $0.25/M input, $1.50/M output
GPT-5.4 Nano
API-only model
400,000 token context · $0.20/M input, $1.25/M output
GPT-5.6 Luna
API-only model
1,050,000 token context · $0.20/M input, $1.20/M output

More text models from inference-net

Questions people ask

Can I run Schematron V2 Small locally?: Yes — the weights are open and hosted on Hugging Face under inference-net/schematron-v2-llama-3.2-3b, so you can download and run it yourself.
What does it cost and how much context does it have?: Via Inference.net the API is priced at $0.05 per million input tokens and $0.23 per million output tokens, with a 128,000-token context window.
How do I give it extraction instructions?: You do not use system or user prompts for instructions — the model expects a JSON schema supplied through the response_format parameter, and that schema defines what it extracts.

Captain's verdict
A surgical tool: if your pipeline needs HTML turned into clean JSON at low cost, Schematron V2 Small earns its place; ask it anything else and you will be disappointed.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Qwen2.5 VL 72B Instruct

TEXT / LLM

Qwen3 8B

TEXT / LLM

AI Models for Image, Video & Text Generation

Schematron V2 Small is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm inference-net data extraction local budget fast

Browse by Model Family