← all releases
Sarvam AI·Feb 5, 2026·v1.0·open source

Sarvam Vision

Sarvam Vision is a 3-billion parameter vision-language model developed by Sarvam AI, designed to perform a range of visual understanding tasks, including image captioning, scene text recognition, chart interpretation, and complex table parsing. It aims to address the challenges of document intelligence, particularly for Indian languages, by unlocking knowledge embedded in physical documents, scanned archives, and historical collections.

OCRLLMLLMs
visit website playground ↗
overview

Sarvam Vision is a 3-billion parameter vision-language model developed by Sarvam AI, designed to perform a range of visual understanding tasks, including image captioning, scene text recognition, chart interpretation, and complex table parsing. It aims to address the challenges of document intelligence, particularly for Indian languages, by unlocking knowledge embedded in physical documents, scanned archives, and historical collections.

key features
  • 01Image captioning
  • 02Scene text recognition
  • 03Chart interpretation
  • 04Complex table parsing
  • 05High accuracy for Indian languages
related productsbrowse all →
Protenixopen sourceProtenix is an open-source, trainable PyTorch implementation of AlphaFold 3, designed for high-accuracy biomolecular structure prediction. It aims to advance accessible and extensible research tools for the computational biology community. ([github.com](https://github.com/bytedance/Protenix?utm_source=openai))Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.Z-Imageopen sourceZ-Image is an efficient image generation foundation model developed by Tongyi-MAI, designed to produce high-quality, diverse, and stylistically versatile images. It serves as a robust base for creators, researchers, and developers seeking advanced image generation capabilities.