Schematron V2 Turbo
Fast and lightInference.net · Released September 2026
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads.
It belongs to Inference.net's Schematron line, extraction models that read HTML and emit JSON against a supplied schema rather than answering in prose.
Facts and pricing
- Provider
- Inference.net
- Context window
- 128K tokens
- Input price
- 0.36 credits / 1M tokens ($0.030 raw)
- Output price
- 1.8 credits / 1M tokens ($0.15 raw)
- Vision (image input)
- No
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Schematron V2 Turbo now
What Schematron V2 Turbo is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
Example prompts
Prompts that suit a fast and light model like Schematron V2 Turbo:
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
Inference.net family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Schematron V2 Turbo | 128K | 0.36 | 1.8 | September 2026 |
| Schematron V2 Small | 128K | 0.60 | 2.8 | September 2026 |
Frequently asked questions
- What is Schematron V2 Turbo?
- Schematron V2 Turbo is an AI model by Inference.net. Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads.
- How much does Schematron V2 Turbo cost on Zeplik?
- Input tokens cost 0.36 credits per million and output tokens 1.8 credits per million (1 credit = $0.10; the raw provider rates are $0.030 and $0.15 per million). New accounts start with free credits.
- How long can a conversation with Schematron V2 Turbo be?
- Schematron V2 Turbo has a 128K-token context window (128,000 tokens), which covers the conversation plus any documents you attach.
- Does Schematron V2 Turbo support images and tools?
- Schematron V2 Turbo is text-only and does not support tool calling.
Related models
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.
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks.
More you can do with Schematron V2 Turbo
- 467 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Schematron V2 Turbo or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.