Source-linked AI model

Inference.net: Schematron V2 Turbo

Inference.net: Schematron V2 Turbo is an AI model from inference-net with a 128,000-token context window, priced at $0.03 per 1M tokens for input. Review its sourced specs below; unavailable fields remain unavailable.

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...

Provider

inference-net

Context window

128,000 tokens

Input price

$0.03 per 1M tokens

Output price

$0.15 per 1M tokens

Source

OpenRouter

More inference-net models · Compare this model · Estimate API cost · All models