inference-net
Inference.net: Schematron V2 Turbo
inference-net/schematron-v2-turbo
For $1, you can send approximately:
~794messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.03/M = $0.000210
Output cost per message7,000 x $0.15/M = $0.001050
Total cost per message$0.001260
Messages for $1793.65
Context window
128k
tokens
Max response
8k
tokens
Input price
$0.03
per million tokens
Output price
$0.15
per million tokens
Modalities
Input:textOutput:text
Description
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...