OctoAI and AWS Better Together
OctoAI is a compute service to run, tune, and scale your generative AI, built on top of AWS. It allows developers to quickly and cost effectively take generative AI applications to production on AWS.
Benefits of OctoAI, powered by AWS
OctoAI complements the AWS core infrastructure offerings to ensure models are run in a hardware configuration that is optimized for the model and for the application. OctoAI's model acceleration reduces latency and cost for popular foundation models including Stable Diffusion, Whisper, LLaMA and Falcon, as well as custom models built or trained by customers.
Ease of Use
Ready to use deployment templates for popular OSS models
Customize OSS models
Easily integrate with app dev and model dev workflows
Auto-selection of hardware
Efficiency
Fastest foundation models for generative AI made possible through our model acceleration technology
Accelerate and run your custom models
Flexibility to make price-performance tradeoffs
Make Accessible
Customers may select and run accelerated OSS foundation models, fine tune models, upgrade to new models as they emerge, or bring their own custom models
No lock-in into the model or service
OctoAI powered by AWS
OctoAI Model Acceleration on AWS
Stable Video Diffusion (SVD) 1.1 now on OctoAI empowers developers to easily add engaging animations and motion to GenAI-powered images.
Capitol AI and OctoAI worked together to achieve a 4x improvement in speed and 75% reduction in large language model (LLM) usage costs, through fine-tuned versions of Mistral models.
We’re excited today to announce that Mistral’s Mixtral 8x7B Instruct large language model (LLM) is now available on the OctoAI Text Gen Solution. Customers can get started with Mixtral on OctoAI today.
Your choice of models on our SaaS or in your environment
Run any model or checkpoint on our efficient, reliable, and customizable API endpoints. Sign up and start building in minutes.