inference-nettext → text
Inference.net: Schematron V2 Turbo
Canonical ID: inference-net/schematron-v2-turbo
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...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.03
Completion Output (1M Tokens)
Output$0.15
Prompt KV-Cache Read (1M Tokens)
Cached$0.03
Context Window Capacity
Context125k tokens
Supported Parameters & Features
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p