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:

Value	Behavior
`"low"`	Quick, simple replies
`"medium"`	Balanced depth and speed (default value)
`"high"`	More detailed reasoning and structured answers
`None`	Disables reasoning completely

💡 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 None to 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.

First, install the SDK:

$ pip install -Uqq sarvamai

Then use the following Python code:

1 from sarvamai import SarvamAI
2 
3 # Initialize the SarvamAI client with your API key
4 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5 
6 # Example 1: Using default reasoning_effort (not specified) — defaults to "medium"
7 response = client.chat.completions(
8     model="sarvam-105b",
9     messages=[
10         {"role": "system", "content": "You are a helpful assistant."},
11         {"role": "user", "content": "Summarize the story of the Ramayana."}
12     ],
13     # reasoning_effort not specified → defaults to "medium"
14 )
15 
16 print(response.choices[0].message.content)

1 from sarvamai import SarvamAI
2 
3 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4 
5 # Example 2: Using reasoning_effort = "high" — more detailed, thoughtful response
6 response = client.chat.completions(
7     model="sarvam-105b",
8     messages=[
9         {"role": "system", "content": "You are a helpful assistant."},
10         {"role": "user", "content": "Summarize the story of the Ramayana."}
11     ],
12     reasoning_effort="high"
13 )
14 
15 # Receive assistant's reply as output
16 print(response.choices[0].message.content)

1 from sarvamai import SarvamAI
2 
3 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4 
5 # Example 3: Disabling reasoning completely with reasoning_effort = None
6 response = client.chat.completions(
7     model="sarvam-105b",
8     messages=[
9         {"role": "system", "content": "You are a helpful assistant."},
10         {"role": "user", "content": "What is the capital of India?"}
11     ],
12     reasoning_effort=None  # Disables reasoning for fastest response
13 )
14 
15 # Receive assistant's reply as output
16 print(response.choices[0].message.content)

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:

Value	Behavior
`"low"`	Quick, simple replies
`"medium"`	Balanced depth and speed (default value)
`"high"`	More detailed reasoning and structured answers
`None`	Disables reasoning completely

💡 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 None to 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.

First, install the SDK:

$ pip install -Uqq sarvamai

Then use the following Python code:

1 from sarvamai import SarvamAI
2 
3 # Initialize the SarvamAI client with your API key
4 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5 
6 # Example 1: Using default reasoning_effort (not specified) — defaults to "medium"
7 response = client.chat.completions(
8     model="sarvam-105b",
9     messages=[
10         {"role": "system", "content": "You are a helpful assistant."},
11         {"role": "user", "content": "Summarize the story of the Ramayana."}
12     ],
13     # reasoning_effort not specified → defaults to "medium"
14 )
15 
16 print(response.choices[0].message.content)

1 from sarvamai import SarvamAI
2 
3 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4 
5 # Example 2: Using reasoning_effort = "high" — more detailed, thoughtful response
6 response = client.chat.completions(
7     model="sarvam-105b",
8     messages=[
9         {"role": "system", "content": "You are a helpful assistant."},
10         {"role": "user", "content": "Summarize the story of the Ramayana."}
11     ],
12     reasoning_effort="high"
13 )
14 
15 # Receive assistant's reply as output
16 print(response.choices[0].message.content)

1 from sarvamai import SarvamAI
2 
3 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4 
5 # Example 3: Disabling reasoning completely with reasoning_effort = None
6 response = client.chat.completions(
7     model="sarvam-105b",
8     messages=[
9         {"role": "system", "content": "You are a helpful assistant."},
10         {"role": "user", "content": "What is the capital of India?"}
11     ],
12     reasoning_effort=None  # Disables reasoning for fastest response
13 )
14 
15 # Receive assistant's reply as output
16 print(response.choices[0].message.content)

1	from sarvamai import SarvamAI
2
3	# Initialize the SarvamAI client with your API key
4	client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5
6	# Example 1: Using default reasoning_effort (not specified) — defaults to "medium"
7	response = client.chat.completions(
8	model="sarvam-105b",
9	messages=[
10	{"role": "system", "content": "You are a helpful assistant."},
11	{"role": "user", "content": "Summarize the story of the Ramayana."}
12	],
13	# reasoning_effort not specified → defaults to "medium"
14	)
15
16	print(response.choices[0].message.content)

1	from sarvamai import SarvamAI
2
3	client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4
5	# Example 2: Using reasoning_effort = "high" — more detailed, thoughtful response
6	response = client.chat.completions(
7	model="sarvam-105b",
8	messages=[
9	{"role": "system", "content": "You are a helpful assistant."},
10	{"role": "user", "content": "Summarize the story of the Ramayana."}
11	],
12	reasoning_effort="high"
13	)
14
15	# Receive assistant's reply as output
16	print(response.choices[0].message.content)

1	from sarvamai import SarvamAI
2
3	client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4
5	# Example 3: Disabling reasoning completely with reasoning_effort = None
6	response = client.chat.completions(
7	model="sarvam-105b",
8	messages=[
9	{"role": "system", "content": "You are a helpful assistant."},
10	{"role": "user", "content": "What is the capital of India?"}
11	],
12	reasoning_effort=None # Disables reasoning for fastest response
13	)
14
15	# Receive assistant's reply as output
16	print(response.choices[0].message.content)