Schematron V2 Turbo
by 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 responseformat rather...
- Input / 1M tokens
- $0.03
- Output / 1M tokens
- $0.15
- Context
- 128K
Specs
| Input price | $0.03 / 1M tokens |
|---|---|
| Output price | $0.15 / 1M tokens |
| Cached input | $0.03 / 1M tokens |
| Context window | 128K tokens |
| Max output | 8.19K tokens |
| Reads | text |
| Writes | text |
| Tool calling | No |
| Reasoning | No |
| Listed | Sep 12, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
2 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|
| InferenceNet | bf16 | 128K | 8.19K | $0.03 | $0.15 | $0.03 | 695 ms | 60 tok/s | Normal | |
| InferenceNet | bf16 | 128K | 8.19K | $0.03 | $0.15 | $0.03 | 1.11 s | 62 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- Inference.net
Schematron V2 Small
- Input
- $0.05
- Output
- $0.23
- Context
- 128K
- Qwen
Qwen3.7 Flash
- Input
- $0.03
- Output
- $0.13
- Context
- 1M
- OpenAI
gpt-oss-120b (batch)
- Input
- $0.0296
- Output
- $0.136
- Context
- 131K
- Mistral
Mistral Nemo
- Input
- $0.029
- Output
- $0.03
- Context
- 131K
- Meta
Llama 3.2 1B Instruct
- Input
- $0.027
- Output
- $0.201
- Context
- 60K
- Nex AGI
Nex-N2.5-Mini
- Input
- $0.025
- Output
- $0.10
- Context
- 262K