Prices / Inference Net
Inference.net: Schematron V2 Turbo
Inference Net · 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...
- Input / 1M
- $0.03 · ₹2.87$0.03€0.0268£0.0227SGD 0.0384A$0.043CA$0.0428¥5CHF 0.0249HK$0.2356CN¥0.2006 · ₹3.39 with GST
- Output / 1M
- $0.15 · ₹14.36$0.15€0.134£0.1133SGD 0.192A$0.2152CA$0.2138¥24CHF 0.1247HK$1.18CN¥1 · ₹16.95 with GST
- Context
- 128K
- Sample month
- $0.18 · ₹17.23$0.18€0.1607£0.1359SGD 0.2304A$0.2583CA$0.2566¥29CHF 0.1497HK$1.41CN¥1.2 · ₹20.34 with GST
Sample workload: 100,000 input tokens and 20,000 output tokens per day for 30 days.
Cheaper alternatives
- Apodex: Apodex 1.1 Mini (free) · $0 in / $0 out
- Cohere: North Mini Code (free) · $0 in / $0 out
- Dots Studio: Dots3-Note Preview (free) · $0 in / $0 out
- Google: Gemma 4 26B A4B (free) · $0 in / $0 out
- Google: Gemma 4 31B (free) · $0 in / $0 out
Questions
What is the Inference.net: Schematron V2 Turbo API price per 1 million tokens?
Inference.net: Schematron V2 Turbo is listed at $0.03 input and $0.15 output per 1 million tokens in this snapshot. INR without GST is ₹2.87 input and ₹14.36 output. With 18% GST those INR amounts are ₹3.39 and ₹16.95.
What would Inference.net: Schematron V2 Turbo cost for a sample month?
For 100,000 input tokens and 20,000 output tokens per day for 30 days, this snapshot prices Inference.net: Schematron V2 Turbo at $0.18, ₹17.23 without GST, and ₹20.34 with 18% GST.
Last updated: