Inference.net: Schematron V2 Small
INFERENCE-NET Developer Architecture Profile
Intelligence (ELO)1042Chatbot Arena Verified
Max Context Limit128,000Max Out: 4,096 tokens
Prompt CachingStandard$0.05 / 1M cached
Standard API / 1M$0.28Blended Standard Rate
Model Capabilities & Contract SLAs
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...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.05 / 1M
⚡ Cached Input (Prompt Cache Read)% OFF$0.05 / 1M
Output Tokens (Completion)$0.23 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupInference.net: Schematron V2 Small vs Qwen: Qwen2.5 7B InstructVS Engine MatchupInference.net: Schematron V2 Small vs Mistral: Mistral NemoVS Engine MatchupInference.net: Schematron V2 Small vs Body Builder (beta)VS Engine MatchupInference.net: Schematron V2 Small vs Xiaomi: MiMo-V2.5VS Engine MatchupInference.net: Schematron V2 Small vs OpenAI: gpt-oss-20b (batch)VS Engine MatchupInference.net: Schematron V2 Small vs Microsoft: Phi 4