From the source
Achieves state-of-the-art on global and Indic benchmarks with new capabilities for structured extraction and Indic handwritten recognition Introduction Sarvam Vision, launched as part of our sovereign models line up in February 2026, delivered frontier performance on document intelligence.
While being a general vision-language model (VLM), the model focused on optical character recognition (OCR) capabilities for Indic, table parsing, multilingual visual reasoning, and structured outputs from visual data.
Since launch the model adoption has grown widely and we received important feedback on the areas of improvement.
These signals were primarily along two axes: (a) certain capabilities (or lack thereof) and (b) practical concerns around usability.
For the usability concerns, we focused on making optimizations to the inference stack.
This enabled serving the model at a cheaper price point than we had announced at launch.
Furthermore, the model API is now optimized for production workloads as a result.
…
