Como uso os modelos de Inference Net pela API do OpenRouter?

O OpenRouter disponibiliza 2 modelos de Inference Net por meio de uma única API compatível com a OpenAI. Crie uma chave de API do OpenRouter, aponte seu cliente para https://openrouter.ai/api/v1 e defina o modelo com um ID como inference-net/schematron-v2-turbo. O guia de início rápido contém exemplos de requisições para cada SDK compatível.

Qual modelo de Inference Net tem a maior janela de contexto?

Schematron V2 Turbo tem a maior janela de contexto entre todos os modelos de Inference Net no OpenRouter, aceitando até 128.000 tokens por solicitação.

Qual é o modelo mais recente de Inference Net no OpenRouter?

Schematron V2 Turbo é o modelo de Inference Net adicionado mais recentemente ao OpenRouter, listado em 12 de setembro de 2026.

Inference Net

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

Inference Net tokens processados no OpenRouter

Inference.net: Schematron V2 TurboSchematron V2 Turbo
141M 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.
por inference-net12 de set. de 2026128K de contextoUS$ 0,03/M entrada tokensUS$ 0,15/M saída tokens
Inference.net: Schematron V2 SmallSchematron V2 Small
58,6M 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.
por inference-net12 de set. de 2026128K de contextoUS$ 0,05/M entrada tokensUS$ 0,23/M saída tokens

Inference Net

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

Inference Net tokens processados no OpenRouter

Inference.net: Schematron V2 TurboSchematron V2 Turbo
141M 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.
por inference-net12 de set. de 2026128K de contextoUS$ 0,03/M entrada tokensUS$ 0,15/M saída tokens
Inference.net: Schematron V2 SmallSchematron V2 Small
58,6M 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.
por inference-net12 de set. de 2026128K de contextoUS$ 0,05/M entrada tokensUS$ 0,23/M saída tokens

Inference Net

Perguntas frequentes

Inference Net

Perguntas frequentes