OctoAI Models
OctoAI has a large variety of models from the world's most popular image generation model, Stable Diffusion, to large language models like Llama 2-7B Chat and Llama 2-70B Chat.
Featured Models
We are working to add the most valuable models to OctoAI, and our ML experts apply sophisticated acceleration techniques to vastly improve the performance of these models.
Stable Diffusion 1.5 (accelerated)
Run the world’s fastest and cheapest Stable Diffusion endpoint today in OctoAI.
5x
faster than baseline model
~3,000
images generated for ~$1
Llama 2 7B Chat
Llama 2 7B Chat is an instruction-tuned large language model for chatbots and chat completions.
Whisper X (accelerated)
A general-purpose speech transcription model turning audio speech into text. It is trained on a large diverse dataset of audio and can perform multilingual speech: transcription, translation, and language identification.
6x
cheaper on OctoAI
All Models
OctoAI has some of the most popular open source models today including: Stable Diffusion, Llama 2, and Whisper.
Whisper X (accelerated)
A general-purpose speech transcription model turning audio speech into text. It is trained on a large diverse dataset of audio and can perform multilingual speech: transcription, translation, and language identification.
Stable Diffusion 1.5 (accelerated)
Run the world’s fastest and cheapest Stable Diffusion endpoint today in OctoAI.
Llama 2 7B Chat
Llama 2 7B Chat is an instruction-tuned large language model for chatbots and chat completions.
Falcon 7B Instruct (accelerated)
Falcon-7B Instruct, a state-of-the-art model for completing conversational tasks when given an instruction.
Audio to Text
Whisper X (accelerated)
A general-purpose speech transcription model turning audio speech into text. It is trained on a large diverse dataset of audio and can perform multilingual speech: transcription, translation, and language identification.
Start building with ease in minutes using OctoAI
Our mission is empowering developers to build AI applications that delight users by leveraging fast models running on the most efficient hardware. Sign up and start building in minutes.
