Can I run Schematron V2 Turbo locally?

Yes, the weights are open and the model is hosted on Hugging Face under the repository inference-net/schematron-v2-granite-4.0-h-micro, so you can download and run it yourself.

What does it cost and how long is the context window?

Inference.net prices it at $0.03 per million input tokens and $0.15 per million output tokens, with a 128,000-token context window.

How is this different from a general LLM doing extraction?

Schematron V2 Turbo accepts no extraction instructions through prompts at all — the schema you pass in response_format is the only way to tell it what to pull out, which keeps it fast and consistent but makes it useless for anything else.

Schematron V2 Turbo

1427°

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

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 | $0.03/M input, $0.15/M output. Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. 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

Open weights vs open source vs API-only: what you are actually allowed to do

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 Turbo is a 3-billion-parameter model from Inference.net built for one job: turning HTML into structured JSON at scale. It is unusually narrow by design — you drive it entirely through a JSON schema in the response_format field, not through prompts. If you need to extract structured data from web pages in bulk and want something small, cheap and fast, this is worth a look.

Known for

Dedicated HTML-to-JSON extraction, not a general-purpose model
3B parameters keeps it fast and cheap for high-volume pipelines
Extraction logic lives in the JSON schema, not in your prompt
Open weights available on Hugging Face
Very low token prices suit large-scale scraping workloads

Watch out for

Useless for anything outside structured data extraction — do not bring it a writing or reasoning task.
Instructions via system or user prompts are ignored; your schema must do all the work.
Licence terms are not published by the maker, so check before commercial deployment.

Best for

Prompts to try

Extract a product listing

Paste the raw HTML of an e-commerce product page below, then call this model with a response_format schema that captures name, price, currency, availability, and a list of bullet-point features. Observe how the model ignores any text in this message and works entirely from the schema you supply.

Parse a news article

Take the full HTML source of a news article and supply a JSON schema requesting headline, author, publication date in ISO 8601, summary of up to three sentences, and a list of named entities mentioned. Submit it and inspect the structured output.

Scrape a job posting

Feed the raw HTML of a job listing page and define a schema with fields for job title, company name, location, salary range, required skills as an array, and application deadline. Run it across ten listings to test consistency at small batch scale.

Compare with

Schematron V2 Small
Open-weights model
128,000 token context · $0.05/M input, $0.23/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 Turbo locally?: Yes, the weights are open and the model is hosted on Hugging Face under the repository inference-net/schematron-v2-granite-4.0-h-micro, so you can download and run it yourself.
What does it cost and how long is the context window?: Inference.net prices it at $0.03 per million input tokens and $0.15 per million output tokens, with a 128,000-token context window.
How is this different from a general LLM doing extraction?: Schematron V2 Turbo accepts no extraction instructions through prompts at all — the schema you pass in response_format is the only way to tell it what to pull out, which keeps it fast and consistent but makes it useless for anything else.

Captain's verdict
A ruthlessly single-purpose extraction engine: cheap, fast and open, but only worth touching if structured HTML parsing is your actual problem.

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

AI Models for Image, Video & Text Generation

Schematron V2 Turbo 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 fast budget local

Browse by Model Family