Sarvam: Sarvam 105B
SarvamFeb 18, 2026
sarvam/sarvam-105b
Context Length128,000
Input Price$0.04/1M tokens
Output Price$0.16/1M tokens
Blended Price$0.07/1M tokens
Sarvam 105B is Sarvam AI's flagship open-source Mixture-of-Experts (MoE) large language model (LLM), trained from scratch as India's first competitive 105-billion-parameter model. It delivers state-of-the-art performance across Indian languages and excels in enterprise-grade applications, with strong capabilities in multi-step reasoning, mathematics, coding, knowledge retrieval, and instruction-following.
Input Modalitiestext
Output Modalitiestext
Modalitytext->text
Provider Details
sarvam
Input Cost$0.04/1M tokens
Output Cost$0.16/1M tokens
Context Length128,000
Max Output128,000
Latency-
Throughput-
Supported Parameters
Parameter
Core (Sampling & basic generation)
max_tokensMaximum tokens to generate.
nNumber of completions to generate.
seedSeed for deterministic sampling.
stopSequences where generation stops.
temperatureControls randomness of output.
top_pNucleus sampling threshold.
Penalties (Token Penalties)
frequency_penaltyPenalizes frequent tokens.
presence_penaltyPenalizes tokens already present.
Reasoning (Reasoning Controls)
include_reasoningInclude reasoning trace in the response.
reasoningProvider-specific reasoning configuration.
Throughput
Latency
Make Your First API Call
Get started by making your first request to FastRouter. Use your favorite SDK or make direct API calls.
Copy
from openai import OpenAI
client = OpenAI(
base_url="https://api.fastrouter.ai/api/v1", # FastRouter base URL
api_key= "<FASTROUTER_API_KEY>", # Replace with your FastRouter API key
)
completion = client.chat.completions.create(
model="sarvam/sarvam-105b", # Replace with your model ID
messages=[
{ "role": "user", "content": "What is the meaning of life?" }
]
)
print(completion.choices[0].message.content)
Before you run this code:
- Replace
<FASTROUTER_API_KEY>with your actual API key - Install the OpenAI SDK:
pip install openai - Run the code, then check your dashboard for analytics
Frequently Asked Questions
More models from Sarvam
Model scores sourced from ArtificialAnalysis