Schematron V2 Small

Inference Net · inference-net/schematron-v2-small

← Back to leaderboard

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...

Schematron V2 Small ranks #74 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.14 blended per million tokens, it is cheaper than 88% of models with published API pricing. Its 128,000-token context window is 2.0× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 128000
Max output: 4096

Pricing

Input / 1M: 0.05
Output / 1M: 0.23
Blend / 1M: 0.14

Quality

Quality index:

Provider

Provider: Inference Net
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.14per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.14
10,000,000$1.40
100,000,000$14.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from Inference Net