Schematron V2 Turbo
StandardInference.net's high-throughput extraction specialist: a 3B model that turns HTML pages into structured JSON.
Same schema-driven extraction as Schematron V2 Small, prioritizing throughput for high-volume workloads. Extraction instructions go in a response_format JSON schema rather than system or user prompts. An extraction specialist, not a general-purpose chat model.
▼
Schematron V2 Turbo is somewhat expensive at $0.03/M tokens input and $0.15/M tokens output. Cached input reads are priced at $0.03/M tokens, making repeated context cheaper. The model supports a 128K context window.
Benchmarks
Specifications
Performance
Providers
Misc
Compare with
GPT 6 Astravs Schematron V2 TurboGPT 6.1 Sol Provs Schematron V2 TurboGPT 6.1 Solvs Schematron V2 TurboGPT 6 Luna Provs Schematron V2 TurboGPT 6 Lunavs Schematron V2 Turbo
Claude Fable 5.1vs Schematron V2 TurboClaude Opus 5.5vs Schematron V2 TurboClaude Sonnet 5.5vs Schematron V2 TurboClaude Haiku 5.5vs Schematron V2 Turbo
Gemini 3.8 Flashvs Schematron V2 TurboGemini 3.5 Flash-Litevs Schematron V2 TurboGemma 4 31Bvs Schematron V2 Turbo
Grok 4.7vs Schematron V2 TurboGrok Build 0.1vs Schematron V2 Turbo
Muse Spark 1.3vs Schematron V2 Turbo
DeepSeek V4 Pro (0813)vs Schematron V2 TurboDeepSeek V4.1 Flashvs Schematron V2 Turbo
MiniMax M3vs Schematron V2 Turbo
Kimi K3vs Schematron V2 TurboKimi K2.7 Codevs Schematron V2 Turbo
GLM 5.3vs Schematron V2 TurboGLM 5.3 Flashvs Schematron V2 Turbo
Qwen3.8 Max (0902)vs Schematron V2 TurboQwen3 Coder Nextvs Schematron V2 Turbo
Nemotron 3 Ultravs Schematron V2 TurboFrequently Asked Questions about Schematron V2 Turbo▼
When was Schematron V2 Turbo released?
▼
Schematron V2 Turbo was released on September 12, 2026.
Who created Schematron V2 Turbo?
▼
Schematron V2 Turbo was created by Inference.net.
How much does Schematron V2 Turbo cost?
▼
Schematron V2 Turbo costs $0.03/M input tokens and $0.15/M output tokens.
What is Schematron V2 Turbo API pricing?
▼
The Schematron V2 Turbo API is priced at $0.03 per million input tokens and $0.15 per million output tokens. You can access Schematron V2 Turbo through idapt.app alongside 200+ other AI models in one workspace.
Is Schematron V2 Turbo a reasoning model?
▼
No, Schematron V2 Turbo is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Schematron V2 Turbo support image or vision input?
▼
No, Schematron V2 Turbo does not currently support image or vision input. It is a text-only model.
Does Schematron V2 Turbo support audio?
▼
No, Schematron V2 Turbo does not support audio input.
What is the context window of Schematron V2 Turbo?
▼
Schematron V2 Turbo has a context window of 128K tokens, meaning it can process approximately 96,000 words of context at once.
Is Schematron V2 Turbo open source?
▼
Schematron V2 Turbo is a proprietary model developed by Inference.net. The model weights and training data are not publicly available.
Where can I use Schematron V2 Turbo?
▼
You can chat with Schematron V2 Turbo on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Schematron V2 Turbo through Inference.net's own API or platform.