Context128k
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.
Performance
Latency (p50)—
Throughput (p50)—
Pricing
Input$0.02/M tokens
Output$0.11/M tokens
Cached input$0.02/M tokens
Features
Inputtext
Outputtext
APIResponses, Chat Completions, Messages