How to control response randomness with temperature

The temperature parameter controls how random or deterministic the model’s responses will be.

Range: 0 to 2
Default: 0.2

Lower temperature → more focused, predictable answers (e.g. 0.2)
Higher temperature → more creative, varied responses (e.g. 0.8 or 1.0)

👉 Tip: For most use cases, values between 0.2 and 0.8 give good results.

How it works:

Mode	Recommended `temperature`	Behavior
Non-thinking mode	`0.2` (default)	Straightforward, factual responses
Thinking mode	`0.5` or higher	Deeper reasoning, more exploration
Highly creative	`0.8` - `1.0`	Storytelling, brainstorming, poetry
Very random / playful	`> 1.0`	Unexpected, experimental output

1 # Install SarvamAI
2 !pip install -Uqq sarvamai
3 from sarvamai import SarvamAI

1 # Initialize the SarvamAI client with your API key
2 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

1 # Example1: Using default temperature (0.2) — straightforward, factual response
2 response = client.chat.completions(
3     messages=[
4         {"role": "system", "content": "You are a helpful assistant."},
5         {"role": "user", "content": "Explain the concept of gravity."}
6     ]
7     # temperature is not specified → uses default 0.2
8 )

1 # Example2: Using temperature = 0.9 — more creative, varied response
2 response = client.chat.completions(
3     messages=[
4         {"role": "system", "content": "You are a creative storyteller."},
5         {"role": "user", "content": "Tell me a story about a magical tiger."}
6     ]
7     temperature=0.9  # More creative storytelling
8 )

1 # Receive assistant's reply as output.
2 print(response.choices[0].message.content)