---
id: "inference-net/schematron-v2-turbo"
also: ["inference-net/schematron-v2-turbo-20260902", "inference-net/schematron-v2-granite-4.0-h-micro", "vercel/inference-net/schematron-v2-turbo"]
card_usd_per_m: "0.03 in, 0.15 out, at inference-net"
cheapest_list_usd_per_m: "0.03 in, 0.15 out, at inference-net on openrouter"
cheapest_effective_usd_per_m: "0.0297 in, 0.148 out, at inference-net/bf16 on openrouter"
context: 128000
max_output: 8192
input: ["text"]
output: ["text"]
released: "2026-09-12"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p"]
endpoints: 5
gateways: "openrouter (3), vercel (2)"
no_training: 2
trains: 2
retains_prompts: 2
---
# Inference.net: Schematron V2 Turbo

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...