Reasoning allows models to provide transparent insight into their thought process by generating reasoning tokens before producing their final response. These reasoning tokens show the step-by-step logic the model uses to arrive at its answer.
reasoning_effort
parameter within the chat.completions.create
method. This parameter controls the amount of reasoning the model performs.
Initial Setup
Using Reasoning
reasoning_effort
parameter within the chat.completions.create
method to enable reasoning capabilities.reasoning_effort
parameter accepts the following values:
"none"
- No explicit reasoning effort specified (model-dependent default)"low"
- Minimal reasoning, faster responses"medium"
- Moderate reasoning"high"
- Extensive reasoning, more thorough analysis"none"
will be treated as "medium"
for OpenAI models.
reasoning
field containing the model’s internal thought process: