---
title: "Krutrim models: release history and timeline"
description: "Ola Group AI company in Bengaluru that built the Krutrim family of Indian-language text, vision, speech and OCR models and serves models through Krutrim Cloud."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/krutrim"
markdown_url: "https://theaiengineering.com/releases/krutrim.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-03-11"
citation: "The AI Engineering Editors. \"Krutrim models: release history and timeline.\" The AI Engineering, updated Mar 11, 2026. https://theaiengineering.com/releases/krutrim"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# Krutrim models: release history and timeline

Ola Group AI company in Bengaluru that built the Krutrim family of Indian-language text, vision, speech and OCR models and serves models through Krutrim Cloud.

- Headquarters: Bengaluru, India
- Website: https://www.olakrutrim.com

9 releases from 1 lab, 8 with open weights. Dates are the labs' official announcement dates.

## March 2026

### Chitranuvad

Chitranuvad is a multimodal translation model from Krutrim AI Labs that uses an accompanying image to guide translation from English into Indian languages. It is a fine-tuned version of the Chitrarth-1 vision-language model.

- Date: 2026-03-11
- Lab: Krutrim
- Type: Multimodal
- Weights: Open weights
- Modalities: image, text → text
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/03#krutrim-chitranuvad

Highlights:

- Translates English into Hindi, Bengali and Malayalam, and also handles text-only translation and image captioning
- Built for the English-to-low-resource multimodal translation shared task at WMT 2024, where Krutrim says it was the winning entry
- Trained in three stages: image-text feature alignment, multimodal instruction tuning and translation-specific fine-tuning
- Weights and inference code arrived on Hugging Face and GitHub about a year after Krutrim posted the system description on arXiv in February 2025

Source: [krutrim-ai-labs/Chitranuvad · Hugging Face](https://huggingface.co/krutrim-ai-labs/Chitranuvad)

### Chitrapathak-1

Chitrapathak-1 is an OCR model from Krutrim AI Labs that transcribes printed document images in ten Indian languages by treating OCR as image-to-text generation. It pairs a CLIP vision encoder with the Krutrim-1 7B language model in a LLaVA-style design.

- Date: 2026-03-11
- Lab: Krutrim
- Type: Multimodal
- Weights: Open weights
- Modalities: image → text
- Parameters: 7B language model plus CLIP ViT-L/14 vision encoder
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/03#krutrim-chitrapathak-1

Highlights:

- Covers Hindi, Sanskrit, Bengali, Marathi, Tamil, Telugu, Kannada, Malayalam, Punjabi and Odia
- Splits dense pages into aspect-ratio-aware crops plus a global view before encoding them
- Trained in two stages: projector-only pretraining, then joint fine-tuning of the projector and language model on OCR data
- Krutrim's February 2026 arXiv paper on OCR for India reported that its successor, Chitrapathak-2, ran 3 to 6 times faster

Source: [krutrim-ai-labs/Chitrapathak-1 · Hugging Face](https://huggingface.co/krutrim-ai-labs/Chitrapathak-1)

### Chitrapathak-2

Chitrapathak-2 is the second model in Krutrim's Chitrapathak OCR series, fine-tuned from Nanonets-OCR2-3B to transcribe Indian-language book pages and documents. It covers ten Indian languages and English.

- Date: 2026-03-11
- Lab: Krutrim
- Type: Multimodal
- Weights: Open weights
- Modalities: image, text → text
- Parameters: 3B decoder plus vision encoder
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/03#krutrim-chitrapathak-2

Highlights:

- Built by fine-tuning an existing OCR model rather than joining a separate vision encoder and language model, as Chitrapathak-1 did
- Krutrim's arXiv paper reported a 3 to 6 times speedup over Chitrapathak-1
- Krutrim reported the top Telugu result in its comparison and second place in the other languages it tested
- Languages are Hindi, Sanskrit, Bengali, Telugu, Tamil, Marathi, Kannada, Malayalam, Odia, Punjabi and English

Source: [krutrim-ai-labs/Chitrapathak-2 · Hugging Face](https://huggingface.co/krutrim-ai-labs/Chitrapathak-2)

## February 2025

### Krutrim-2

Krutrim-2 is a 12-billion-parameter multilingual language model from Ola's Krutrim, built on the Mistral NeMo architecture and trained for English and 22 Indian languages. It was released the same day Krutrim introduced Krutrim AI Labs.

- Date: 2025-02-04
- Lab: Krutrim
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Context window: 128,000 tokens
- Parameters: 12B
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights, API, Consumer app
- Permalink: https://theaiengineering.com/releases/2025/02#krutrim-2

Highlights:

- 128K-token context window, with supervised fine-tuning followed by direct preference optimization
- Krutrim reported top-three results on 5 of 7 tasks in its BharatBench suite against larger open and commercial models
- Offered at launch in the Krutrim chat app, through the Krutrim Cloud API and as downloadable weights
- Trained between December 2024 and January 2025 on data running up to April 2024

Source: [krutrim-ai-labs/Krutrim-2-instruct · Hugging Face](https://huggingface.co/krutrim-ai-labs/Krutrim-2-instruct)

### Dhwani-1

Dhwani-1 is Krutrim's speech language model built on Krutrim-1, which takes in speech directly instead of relying on a separate speech recognition step. Krutrim open-sourced its speech-to-text translation capability between English and Indian languages.

- Date: 2025-02-03
- Lab: Krutrim
- Type: Speech
- Weights: Open weights
- Modalities: audio, text → text
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2025/02#krutrim-dhwani

Highlights:

- Follows the SALMONN design: Whisper and BEATs encoders feed the Krutrim LLM through a window-level Q-Former, with LoRA adaptation
- Translates speech between English and Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu
- Post-trained with methods from Krutrim's IndicST paper at ICASSP 2025 plus in-house translation data
- Weights were gated behind a click-through form on Hugging Face, with hosted access on Krutrim Cloud

Source: [krutrim-ai-labs/Dhwani · Hugging Face](https://huggingface.co/krutrim-ai-labs/Dhwani)

### Krutrim Translate

Krutrim Translate is a distilled translation model from Krutrim that builds on IndicTrans2 and raises its context length from 256 to 4,096 tokens.

- Date: 2025-02-03
- Lab: Krutrim
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Context window: 4,096 tokens
- Parameters: ~450M
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2025/02#krutrim-translate

Highlights:

- Distilled to 6 encoder and 3 decoder layers; Krutrim reported at least 4 times lower latency than IndicTrans2 and its distilled versions
- Translates in both directions between English and Hindi, Bengali, Kannada, Marathi, Malayalam, Gujarati, Punjabi, Telugu and Tamil
- Trained on AI4Bharat's Bharat Parallel Corpus Collection plus Krutrim's own data
- Weights were gated behind a click-through form on Hugging Face, with hosted access on Krutrim Cloud

Source: [krutrim-ai-labs/Krutrim-Translate · Hugging Face](https://huggingface.co/krutrim-ai-labs/Krutrim-Translate)

### Chitrarth-1

Chitrarth-1 is Krutrim's vision-language model for 10 Indian languages and English, pairing the Krutrim-1 7B language model with a SigLIP image encoder.

- Date: 2025-02-02
- Lab: Krutrim
- Type: Multimodal
- Weights: Open weights
- Modalities: image, text → text
- Parameters: 7.5B
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2025/02#krutrim-chitrarth

Highlights:

- Covers Hindi, Bengali, Telugu, Tamil, Marathi, Gujarati, Kannada, Malayalam, Odia and Assamese
- Krutrim reported that it outperformed IDEFICS 2 (7B) and PALO 7B on most academic multimodal benchmarks it tested
- Introduced with BharatBench, Krutrim's evaluation suite for vision-language models in Indian languages
- Described in a NeurIPS 2024 workshop paper; weights and code released under the Krutrim Community License

Source: [krutrim-ai-labs/Chitrarth · Hugging Face](https://huggingface.co/krutrim-ai-labs/Chitrarth)

### Vyakyarth-1

Vyakyarth-1 is Krutrim's multilingual sentence embedding model for Indian languages, fine-tuned from the STSB-XLM-R multilingual model with a contrastive objective.

- Date: 2025-02-02
- Lab: Krutrim
- Type: Embedding
- Weights: Open weights
- Modalities: text → embedding
- Context window: 128 tokens
- Parameters: 270M
- License: Krutrim Community License Agreement 1.0
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2025/02#krutrim-vyakyarth

Highlights:

- Maps sentences to 768-dimensional vectors for semantic search, retrieval, clustering and classification
- Trained for Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Sanskrit, Tamil and Telugu as well as English
- Krutrim reported higher FLORES Indic-to-English retrieval accuracy than MuRIL, IndicBERT and jina-embeddings-v3
- Accepts inputs of up to 128 tokens

Source: [krutrim-ai-labs/Vyakyarth · Hugging Face](https://huggingface.co/krutrim-ai-labs/Vyakyarth)

## December 2023

### Krutrim-1

Krutrim was the first foundation language model from Ola's AI company of the same name, trained from scratch on more than 2 trillion tokens with a large share of Indian-language data. Krutrim later published it as the 7B Krutrim-1.

- Date: 2023-12-15
- Lab: Krutrim
- Type: LLM
- Weights: Proprietary
- Modalities: text → text
- Context window: 4,096 tokens
- Parameters: 7B
- Permalink: https://theaiengineering.com/releases/2023/12#krutrim-1

Highlights:

- Unveiled at a livestreamed launch on December 15, 2023, with a waitlist for its chat assistant and for developers
- At launch Krutrim said it supported all 22 scheduled languages and generated text in Hindi, English and 8 other Indian languages
- Announced alongside Krutrim Pro, a larger multimodal model planned for later release
- Weights were released on Hugging Face as Krutrim-1 under the Krutrim Community License in February 2025

Source: [Press release - Ola Krutrim Blog](https://blog.olakrutrim.com/press-release/)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "Krutrim models: release history and timeline." The AI Engineering, updated Mar 11, 2026. https://theaiengineering.com/releases/krutrim

HTML link:

```html
<a href="https://theaiengineering.com/releases/krutrim">Krutrim models: release history and timeline</a> (The AI Engineering)
```

- Title: Krutrim models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-03-11
- URL: https://theaiengineering.com/releases/krutrim
- Markdown: https://theaiengineering.com/releases/krutrim.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
