Costs less than most peers
Market median price: $0.06 blended / 1M, cheaper than 6 of 6 priced peers.
Inference Net · Chat
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net, tuned for throughput on high-volume extraction workloads. Extraction instructions are supplied as a JSON schema in response_format rather than as a prompt, over a 128K-token context. It does not support tool calling.
Evidence and sources
Market median price: $0.06 blended / 1M, cheaper than 6 of 6 priced peers.
The weights aren't public, so you can't run it yourself.
Also known as: inference-net/schematron-v2-turbo
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works