SUTRA-ONLINE models are online LLMs pioneered by Two Platforms. They are online LLMs because they can use knowledge from the internet, and thus leverage the most up-to-date information when forming response. By providing SUTRA-Online knowledge from web, they can accurately respond to time sensitive queries, unlocking knowledge beyond its training corpus. This means that SUTRA models can respond to queries like “Who won in yesterday’s India vs England cricket match?” accurately, whereas offline models like Llama2, GPT-3.5 etc. suffer from knowledge cut-off dates. Following example shows how SUTRA-Online series models respond to queries with up-to-date information, without suffering from knowledge cut-off dates from training set.

SUTRA-ONLINE response for “Who won in yesterday’s India vs England cricket match?” (as of 02/20/2024)

India won the cricket match against Eng
land yesterday with a thumping 434-run
victory. Ravindra Jadeja took five wickets
as England collapsed. It was quite a
smashing win for India!

GPT-3.5 response for “Who won in yesterday’s India vs England cricket match?” (as of 02/20/2024)

I'm sorry, but I cannot provide real-time
information or updates as my training
data only goes up until January 2022, and
I do not have access to the internet.
ase check a reliable sports news website
or app for the latest cricket match results
between India and England.


SUTRA-LIGHT models are extensively multilingual language models adept at executing instructions in 50+ languages, with special emphasis on Latin (English, Italian, French), Indic Languages (Hindi, Gujarati, Tamil etc.) and far eastern languages (e.g. Korean). Developed using a diverse mix of instructions from our proprietary and leading open-access datasets, it achieves state-of-the-art performance across numerous multilingual benchmarks. Following example of response in Hindi showcases the nuance with with SUTRA-Light can answer, understanding the context specificity of language.

SUTRA-LIGHT response for “बहुत बढ़िया! स्मोक्ड सैल्मन क्या है? (Great, what is a smoked salmon?)”

चूल्हे में पकाने के समान गहरा स्वाद पाने के लिए सैल्मन को नमक
के साथ संरक्षित किया जाता है और फिर भाप पर पकाया जाता है
(Smoked salmon is salmon that has been cured
and then smoked, offering a rich, smoky flavor)

GPT-3.5 response for the same question

स्मोस्मोक्ड सैल्मन वह सैल्मन है जिसे ठीक किया गया है और फिर धूम्रपान
किया जाता है, जिससे इसमें एक समृद्ध, धूम्रपान वाला स्वाद आता है।
(Smoked salmon is a salmon which is corrected, then
it smokes a cigarette and gets a smoked flavor)


SUTRA-AVATAR are visual generative AI models that enable realtime interactions with photorealistic AI avatars. These models can create photorealistic AI characters in full HD resolution, complete with emotions, gestures, and synchronized natural-sounding voice. SUTRA-AVATAR allows extensive customization, offering a range of appearances, expressions, and emotions to facilitate authentic interactions with synthesized photorealistic artificial characters.

SUTRA-AVATAR can be driven by either text and/or audio and provides the ability to perform realtime and live video calls with AI characters. Models can be accessed either in the form of videos or as a live video stream. The models are light weight and can be accessed via API endpoint. Specific instances of SUTRA-AVATAR are ultra light weight and can run locally on-device.