Skip to content
A clean 2D grid displays stylized, interconnected brain icons as colorful circuit-like dots and lines. Distinct small shapes represent different AI models, radiating around a central, brightly colored brain symbolizing reasoning, with arrows linking models to show selection and varying effort. The image uses five bold, flat colors on a white background, with no gradients, people, or text. The image is simple and compact, sized at 128x128 pixels.

Reasoning Models

The OpenAI reasoning models, the o1, o3 models, DeepSeek R1 or Anthropic Sonet 3.7, are models that are optimized for reasoning tasks.

script({
model: "openai:o1",
})

The reasoning and reasoning-small model aliases are available for reasoning models.

script({
model: "openai:reasoning",
})

or

Terminal window
genaiscript run ... -p openai -m reasoning

GenAIScript automatically extracts the thinking/reasoning content of the LLM responses.

The reasoning effort parameter can be set to low, medium, or high.

  • configured with the reasoningEffort parameter
script({
model: "openai:o3-mini"
reasoningEffort: "high"
})
  • as a tag to the model name
script({
model: "openai:o3-mini:high",
})

For Anthropic Sonnet 3.7, the reasoning efforts are mapped to the following budget_token values:

  • low: 2048
  • medium: 4096
  • high: 16384
  • o1-preview, o1-mini do not support streaming
  • o1 models do not support tool calling so GenAIScript uses fallback tools.

OpenAI provides an extensive advice on prompting reasoning models.