Schematron V2 Turbo

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

← Back to leaderboard

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...

Schematron V2 Turbo ranks #57 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.09 blended per million tokens, it is cheaper than 93% 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: 8192

Pricing

Input / 1M: 0.03
Output / 1M: 0.15
Blend / 1M: 0.09

Quality

Quality index:

Provider

Provider: Inference Net
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.09per 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$0.09
10,000,000$0.90
100,000,000$9.00

Related models

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

More from Inference Net

Closest API price