Inference.net: Schematron V2 Turbo

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net.

Context
128K
Max output
8K
Input price
$0.03/1M tokens
Output price
$0.15/1M tokens

Capabilities

Output Control
Structured Output
JSON Mode

Details

Model IDinference-net/schematron-v2-turbo
Provider OpenRouter
Creator inference-net
Family—
License—
Status—
Type—
Input modalitiestext
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window128K tokens
Max input—
Max output8K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Pricing

Input
$0.03
Output
$0.15
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/inference-net/schematron-v2-turbo