Amazon Bedrock

Mistral AI in Amazon Bedrock

Break new ground with powerful foundation models from Mistral AI

Get started with Mistral AI models in Amazon Bedrock

Meet Mistral AI

Mistral AI is making generative AI accessible to all developers and enterprises, with a strong focus on portability, customization, and efficiency. Its cutting-edge models reflect the company's ambition to become the leading supporter of the generative AI community, and elevate publicly available models to state-of-the-art performance. With Mistral AI models in Amazon Bedrock, customers can experience built-in security, comprehensive AI tools, and a clear path from proof of concept to production. Hear from Marjorie Janiewicz, Mistral’s Global Head of Revenue and US General Manager, as she discusses what makes Mistral’s partnership with AWS unique.

Benefits

Transparency and trust

Mistral AI models are transparent and customizable, appealing to enterprises that have compliance and regulatory requirements. These models are available as white-box solutions, making both weights and code sources available.

Accessible to a wide range of users

Mistral AI models are transparent and customizable. The models are available under the Apache 2.0 license, appealing to enterprises that have compliance and regulatory requirements.

Fast inference speed

Mistral AI models have an impressive inference speed and are optimized for low latency. The models also have a low memory requirement and have high throughput for their respective sizes (7B, 8x7B).

Balance of cost and performance

Mistral AI models strike a remarkable balance between cost-effectiveness and performance. The use of sparse mixture of experts (MoE) makes Mistral AI’s large language models (LLMs) efficient, affordable, and scalable while controlling compute costs.

Use cases

Text summarization

Mistral AI models extract the essence from lengthy articles so you quickly grasp key ideas and core messaging.

Structuration

Mistral AI models deeply understand the underlying structure and architecture of text, organize information within text, and help focus attention on key concepts and relationships.

Question answering

The core AI capabilities of understanding language, reasoning, and learning allow Mistral AI models to handle question answering with more human-like performance. The accuracy, explanation abilities, and versatility of Mistral AI models make them very useful for automating and scaling knowledge sharing.

Code completion

Mistral AI models have an exceptional understanding of natural language and code-related tasks, which is essential for projects that need to juggle computer code and regular language. Mistral AI models can help generate code snippets, suggest bug fixes, and optimize existing code, speeding up your development process.

Customers

Too Good To Go Reduces Food Waste with Mistral AI and AWS

Discover how TooGoodToGo uses Mistral AI models and Amazon Bedrock to gain deep insights into store retention, improve onboarding, and make their marketplace more intuitive, for a future with less food waste.

BigDataCorp uses Mistral AI to reduce analysis costs by 50%

Thoran Rodrigues, CEO of BigDataCorp, describes how the company launched a solution that leverages Mistral AI models in Amazon Bedrock in less than a month. Their solution, Generative Biography, converts structured information that was previously delivered in spreadsheets into text. The product was launched in 20 days—from conception to operation—and has already resulted in a 50% reduction in decision-making costs.

Zalando

"At Zalando, accessing Mistral AI models in Amazon Bedrock has been a game-changer for our multinational operations across Europe. Mistral Large provides exceptional support and native fluency for European languages that empowers our diverse workforce to communicate seamlessly, fostering collaboration and inclusivity by using the models to draft emails in German, French, and other languages. Personally, the model’s German language capabilities have greatly aided my own language learning journey. Mistral's multilingual accuracy and nuanced understanding of grammar and cultural context paired with Amazon Bedrock's secure and serverless single API allows us to deliver exceptional service to our customers across the region."

Samay Kapadia, ML Engineering Manager, Zalando

SuperInsight

"At Superinsight, we process thousands of medical records for individuals in need. By leveraging the Mistral 7B model in Amazon Bedrock, we can efficiently extract data and uncover insights 10x faster, 25x cheaper, and identify 3x more insights that humans often miss, which is crucial in our business since any overlooked evidence can impact the outcome of each case. This powerful combination allows us to deliver superior medical reviews to our attorneys, enabling them to assist more people with disabilities."

Nelson Chu, CEO, Superinsight