Models/Inference-net/Schematron V2 Turbo

Schematron V2 Turbo

Name: Schematron V2 Turbo API access
Brand: Inference-net

Inference-net · Open weights · Released Sep 12, 2026 · inference-net/schematron-v2-turbo

Best $0.03 in / $0.15 out via InferenceNet · bf16

Compare Estimate cost

128K contextStructured outputPrompt cachingOpen weights

Available from 2 providersUSD / MTOK · PRICES 29 MINUTES AGO · SPEED 7 DAYS AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
InferenceNetinference-net/us1ST PARTY	$0.03	$0.15	$0.03	128K	bf16	—	—	100.0%
InferenceNetinference-net/bf161ST PARTY	$0.03	$0.15	$0.03	128K	bf16	0.4s	322 tok/s	100.0%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 7 days ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

Pricing variants · USD / MTok in / out

STANDARD

$0.03 / $0.15

per MTok in / out

CACHE READ $0.03

Recent changesRSS ↗

Sep 12, 2026model added

About

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...

Specifications

Context window128,000

Max output8,192

Modalities intext

Modalities outtext

LicenseOpen weights

ReleasedSep 12, 2026

TokenizerOther

WeightsHugging Face ↗

Schematron V2 Small$0.05 / $0.23

Embed badge

Schematron V2 Turbo price and speed badge

[![Schematron V2 Turbo](https://modelindex.ai/badge/inference-net/schematron-v2-turbo)](https://modelindex.ai/models/inference-net/schematron-v2-turbo)

Sources

OpenRouter API29 minutes ago

AGGREGATOR

ModelIndex benchmarks7 days ago

MEASURED

Verified 29 minutes ago · list prices, not negotiated rates.