Today, we're excited to announce that Together AI is now available on Amazon Web Services (AWS) Marketplace, and has joined the AWS Partner Network (APN). Our platform delivers up to 2-3x faster inference times and optimized performance for leading models like Llama-3.1 and Qwen 2.5, with access to over 200 open-source models. AWS customers can now use their existing cloud credits and committed spend to access our platform, while cutting GPU costs by up to ⅓ compared to closed-source solutions.
AWS customers can now benefit from:
- Accelerated development: Get superior inference speed, performance optimization and fine-tuning across our extensive model library
- Cost efficiency: Reduce GPU consumption significantly while maintaining high performance
- Simplified procurement and billing: Skip pre-approvals with AWS-managed licensing and seamlessly apply your committed cloud spend
{{custom-cta-1}}
Together 🤝 AWS: Accelerating generative AI in the enterprise
As a member of the AWS Partner Network, we're collaborating closely with AWS to accelerate enterprise generative AI development. Our platform complements AWS infrastructure by delivering faster inference, reduced GPU consumption, and improved model orchestration capabilities–helping organizations move from experimentation to production rapidly. Companies can quickly deploy powerful AI solutions for key use cases like intelligent document processing with RAG, automated customer service, and code generation–all with enterprise-grade performance and reliability.
Come meet us at Re:Invent
Join us at Re:Invent to discuss your specific use cases around RAG, fine-tuning, and LLM optimization. Find us at booth #1406 in the MongoDB pavilion – we'd love to show you how Together AI can accelerate your generative AI initiatives.
Ready to get started? Explore our offering on AWS Marketplace or reach out to learn how Together AI can help you take your AI projects to the next level.
Accelerate inference and reduce costs with your existing AWS credits.