How to adjust the model’s thinking level with reasoning_effort
How to adjust the model’s thinking level with reasoning_effort
The reasoning_effort parameter controls how much effort the model puts into reasoning and planning its response.
- Higher effort → more thoughtful, step-by-step, or structured answers
- Lower effort → faster, simpler replies
Allowed values:
💡 Tips:
- Use
"low"when you want short, direct responses. - Use
"medium"for balanced performance (this is the default). - Use
"high"for tasks like explanations, problem solving, reasoning. - Use
Noneto completely disable reasoning when you want the fastest possible responses.
Note:
- Setting higher reasoning effort may increase response time slightly, since the model is thinking more.
- Turning reasoning off also changes the default
temperatureonsarvam-105b, from1.0to0.6.
sarvam-105b-conversations runs with reasoning off only. If you send a reasoning_effort level, the request succeeds but the model doesn’t reason, so you can leave the field out. Its default temperature is 0.6.
First, install the SDK:
Then use the following Python code: