Sarvam Launches Vision 2.1 AI Model for Documents and Indian Languages

Sarvam has launched the latest version of its Vision AI model, with a focus on reading and understanding documents. The model can extract information from forms and tables and turn it into structured digital data. 

Vision 2.1 can also read handwritten text in Indian languages. Sarvam said the model scored 87.3 on the olmOCR-Bench and 87.39 on its own Indic benchmark. 

Better at Forms, Tables and Handwriting 

The new model is designed to handle more complicated documents, including tables spread across multiple pages and forms where information has to be picked out from specific fields. 

It can also recognise handwritten text in Indian languages. This could be useful for converting older or handwritten documents into digital formats. 

Sarvam said it worked on reducing incorrect responses and inconsistent results seen in the earlier version of the model. 

Model Trained on Real and Synthetic Data 

Sarvam said Vision 2.1 was trained using a mix of real-world and synthetic data. The training material included handwritten and printed forms in multiple languages, along with artificially filled-in forms. 

The company then used supervised fine-tuning and reinforcement learning with verifiable rewards to improve the model's results. 

Sarvam first launched its Vision model in February 2026. The earlier version focused on reading text from images and documents, understanding tables and producing structured information. 

Lower Cost of Running the Model 

Sarvam has also made changes to the technology used to run Vision 2.1, which it said allows the model to be offered at a lower cost than originally planned. 

Its API has also been optimised for companies that want to use the model in their own software. 

Vision 2.1 uses a vision-language model along with additional systems that help it understand the layout of a document and the order in which its contents need to be read. 

Read More: ESDS Software Solution Share Price Hits 5% Lower Circuit After Q1 FY27 Earnings Results: Total Income Up 7.5% YoY! 

Conclusion 

Sarvam Vision 2.1 is aimed at businesses and other users that need to process large amounts of documents, forms and tables. The model adds support for handwritten text in Indian languages and is designed to handle more complex documents than the earlier version. 

Disclaimer: This blog has been written exclusively for educational purposes. The securities mentioned are only examples and not recommendations. This does not constitute a personal recommendation/investment advice. It does not aim to influence any individual or entity to make investment decisions. Recipients should conduct their own research and assessments to form an independent opinion about investment decisions.  

Investments in the securities market are subject to market risks, read all the related documents carefully before investing.