Sarvam AI: Sarvam 105B

Flagship Indian-language reasoning model for enterprise multilingual applications

Model lab: Sarvam AI
Model family: sarvam

Modalitiestext → text

Context window131,072

Maximum output131,072

InputUSD 0.032 / 1M tokens

OutputUSD 0.128 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to sarvam/sarvam-105b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "sarvam/sarvam-105b"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Sarvam 105B API Pricing

Type	Price information
Input	USD 0.032 / 1M tokens
Output	USD 0.128 / 1M tokens

Benchmarks

High

Intelligence Index · v4.38.8

Coding Index—

Agentic Index—

Performance

Output speed232.05 tokens/s

Time to first token1.56 s

Time to first answer token—

End-to-end response time—

Measurement variant	Output speed	Time to first token	Time to first answer token	End-to-end response time
High	232.05 tokens/s	1.56 s	—	—

Performance trends

Throughput232.05 tok/sCurrent

Time to first token1.56 sCurrent

End-to-end latency7.8 sCurrent

Throughput

Current232.05 tok/s

Window average230.0 tok/s

Time to first token

Current1.56 s

Window average1.6 s

End-to-end latency

Current7.8 s

Window average7.5 s

Tail latency (P99)

Current14.9 s

Window average17.3 s

Prompt cache hit rate

Current19.3%

Window average24.5%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Sarvam 105B Compare models

Model	Input price	Output price	Context window	Capabilities
Sarvam 105BThis page	USD 0.032 / 1M tokens	USD 0.128 / 1M tokens	131,072	Text output · Reasoning · Tool calling
Sarvam 30B	USD 0.016 / 1M tokens	USD 0.08 / 1M tokens	128,000	Text output · Reasoning · Tool calling
Beam 1.0 501B A23B	USD 0.2 / 1M tokens	USD 0.8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Ling 3.1 Flash	USD 0.06 / 1M tokens	USD 0.176 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Schematron V2 Small	USD 0.04 / 1M tokens	USD 0.184 / 1M tokens	128,000	Text output

Model specifications

Input: text
Output: text
Context window: 131,072
Maximum output: 131,072
Release date: 2025-09-01
Attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Sarvam 105B for?

Flagship Indian-language reasoning model for enterprise multilingual applications

What inputs and outputs does Sarvam 105B support?

Recorded inputs: text; outputs: text.

How is Sarvam 105B priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.032 / 1M tokens; Output USD 0.128 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Sarvam 105B?

Current model records list Context window 131,072 tokens; Maximum output 131,072 tokens.

What model parameter does the Quickstart use?

The example uses sarvam/sarvam-105b. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.