Using Mixtral 8x7B on AWS Bedrock

Quick Start

1. 1
   Create an account at AWS Bedrock and generate an API key.
2. 2
   Use the AWS Bedrock SDK or REST API to call mixtral-8x7b — see the documentation for request format.
3. 3
   You'll be billed $0.45/1M input, $0.70/1M output tokens. See full pricing.

Code Examples

import boto3

# Reads AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION from env
client = boto3.client("bedrock-runtime", region_name="us-east-1")
response = client.converse(
    modelId="mixtral-8x7b",
    messages=[{
        "role": "user",
        "content": [{"text": "Hello"}]
    }]
)
print(response["output"]["message"]["content"][0]["text"])

About AWS Bedrock

Amazon Bedrock is a comprehensive, fully managed service for building and scaling generative AI applications. The platform provides access to a diverse array of high-performing foundation models (FMs) from leading AI companies through a unified API, enabling users to select the most suitable models for their specific use cases. Key features include model customization using proprietary data through techniques like fine-tuning and Retrieval Augmented Generation (RAG), which significantly enhances the relevance and accuracy of AI outputs. Additionally, the platform supports the automation of complex tasks with agents capable of executing multi-step operations, making it versatile for applications ranging from text generation and image creation to conversational AI. Beyond its robust technical capabilities, Amazon Bedrock offers a serverless experience that streamlines infrastructure management, allowing developers to focus on application development without the burden of managing underlying resources. The platform prioritizes security and compliance, ensuring that data remains within the AWS ecosystem and adheres to industry standards. Bedrock's flexible pricing models, including pay-as-you-go options, enable organizations to effectively manage costs while scaling their AI initiatives. This combination of advanced features, ease of use, and cost-effectiveness positions Amazon Bedrock as a powerful tool for businesses looking to innovate rapidly in the generative AI space, ultimately enhancing productivity and operational efficiency.

AWS Bedrock is Amazon's fully managed foundation-model service, providing unified API access to top models from Anthropic, Meta, Mistral, and other leading AI labs with built-in tools for RAG, fine-tuning, and AI agent development.

Pricing on AWS Bedrock

Capabilities

No model capability flags are currently sourced.

About Mixtral 8x7B

Mixtral 8x7B, developed by Mistral AI, features a cutting-edge Mixture of Experts (MoE) architecture, utilizing eight experts with seven billion parameters each, yielding a total of 46.7 billion parameters. This architecture activates only two experts per token, allowing for efficient processing and a 6x faster inference rate compared to Llama 2 70B. The model excels in performance, surpassing Llama 2 70B and competing with GPT-3.5 on numerous benchmarks. It supports multiple languages and can handle context up to 32,000 tokens, enhancing understanding of lengthy text. Designed for diverse tasks, it is strong in code generation and available under a permissive Apache 2.0 license, promoting community engagement. Compatible with various optimization tools, its weights are easily deployable, with Mistral AI continuing to improve its capabilities through performance optimizations and fine-tuning efforts.