Amazon
Amazon Bedrock is Amazon’s enterprise-grade generative AI service platform. Through Bedrock, businesses can access foundation models from leading AI companies, including Anthropic, AI21 Labs, Cohere, Meta, Stability AI, and Amazon’s own models.
Key Features:
- Supports multiple foundation models, including text, image, and embedding models
- Provides comprehensive security and privacy controls
- Supports Function Calling and JSON schema
- High output speed (approximately 97 tokens/sec) with low latency (0.38 seconds)
- Pay-as-you-go pricing model
Pricing (using Nova Pro as an example):
- Input tokens: $0.80 per million tokens
- Output tokens: $3.20 per million tokens
- Blended rate: $1.40 per million tokens (calculated at 3:1 ratio)
Amazon Bedrock provides businesses with a secure and reliable generative AI solution, helping enterprises quickly build and scale AI applications.
Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time cu ...
Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for sp ...
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the- ...
Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time c ...
Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for s ...
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the ...