{"data":{"id":"inference-net/schematron-v2-turbo","canonical_slug":"inference-net/schematron-v2-turbo-20260902","hugging_face_id":"inference-net/schematron-v2-granite-4.0-h-micro","name":"Inference.net: Schematron V2 Turbo","created":1789176949,"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...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000003","completion":"0.00000015","input_cache_read":"0.00000003"},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/inference-net/schematron-v2-turbo-20260902/endpoints"}}}