How do I use Inference Net models through the OpenRouter API?

OpenRouter serves 2 Inference Net models behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as inference-net/schematron-v2-turbo. The quickstart has request examples for every supported SDK.

Which Inference Net model has the largest context window?

Schematron V2 Turbo has the largest context window of any Inference Net model on OpenRouter, accepting up to 128,000 tokens per request.

What is the newest Inference Net model on OpenRouter?

Schematron V2 Turbo is the most recently added Inference Net model on OpenRouter, listed on September 12, 2026.

Inference Net

Access 2 Inference Net models through the OpenRouter unified API including Schematron V2 Turbo and Schematron V2 Small. Compare pricing, context windows, benchmarks, and capabilities between different Inference Net models.

Inference Net tokens processed on OpenRouter

Inference.net: Schematron V2 TurboSchematron V2 Turbo
121M tokens
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 than through system or user prompts.
by inference-netSep 12, 2026128K context$0.03/M input tokens$0.15/M output tokens
Inference.net: Schematron V2 SmallSchematron V2 Small
36.2M tokens
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. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.
by inference-netSep 12, 2026128K context$0.05/M input tokens$0.23/M output tokens

Inference Net

Access 2 Inference Net models through the OpenRouter unified API including Schematron V2 Turbo and Schematron V2 Small. Compare pricing, context windows, benchmarks, and capabilities between different Inference Net models.

Inference Net tokens processed on OpenRouter

Inference.net: Schematron V2 TurboSchematron V2 Turbo
121M tokens
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 than through system or user prompts.
by inference-netSep 12, 2026128K context$0.03/M input tokens$0.15/M output tokens
Inference.net: Schematron V2 SmallSchematron V2 Small
36.2M tokens
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. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.
by inference-netSep 12, 2026128K context$0.05/M input tokens$0.23/M output tokens

Inference Net

Frequently asked questions

Inference Net

Frequently asked questions