Other

Inference.net: Schematron V2 Turbo

inference-net/schematron-v2-turbo

canonical: inference-net/schematron-v2-turbo-20260902

Descriptionfrom OpenRouter

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...

Context length

128,000 tok

Max completion

8,192 tok

Knowledge cutoff

—

Expires

—

Added to OpenRouter

9/12/2026

Cache last refreshed

11/12/2026

Primary modality

text->text

Source

OpenRouter

Input modalities

text

Output modalities

text

Pricing

Field	Per token (USD)	Per million
prompt	0.00000003	$0.030
completion	0.00000015	$0.150
input_cache_read	0.00000003	$0.030

Supported parameters(13)

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p

OpenRouter page Hugging Face