Reasoning Configuration
Você pode configure o reasoning behavior using thereasoning parameter:
Reasoning Intensity
Theeffort parameter controls how much computational resource the model invests in reasoning, essentially dictating the level of reasoning effort.
Using Reasoning in Conversations
The reasoning feature can also be utilized in multi-turn dialogues:Responses Containing Reasoning Information
When reasoning is enabled, the API returns results that include reasoning data:Usage Recommendations
- Escolha the appropriate reasoning effort level: Use
highfor complex issues andlowfor simple tasks. - Consider token usage: Reasoning will increase token consumption.
- Utilize streaming: For longer reasoning chains, streaming can enhance user experience.
- Provide context: Give the model sufficient context to enable effective reasoning.
Última atualização: 2026-06-01