Pricing & Plans
Get started today on OctoAI and receive $10 of free credit in your account.
Products
OctoAI provides products that enable builders to create the next generation of AI applications.
Text Gen Solution
Build on your choice of LLMs like Llama 2, Code Llama, Mistral, and Mixtral against one unified API endpoint, or bring your own checkpoint.
Media Gen Solution
Easily customize (fine-tune) Stable Diffusion models and seamlessly scale usage with no impact to image generation or animation speed or quality.
OctoStack
OctoStack allows you to run your choice of models in your environment, including any cloud platform, VPC, or on-premise, ensuring full control over your data.
Only pay for what you use
OctoAI uses highly sophisticated AI systems expertise to accelerate foundational models. This allows us to pass on the performance gains from lower latency and increased speeds back to you with reduced inference pricing.
Flexibility
Run your choice of models on our reliable and scalable compute
Better user experience
Lower latencies and higher speeds mean your users only experience the snappiest and best app performance
Cost Savings
We pass on the performance improvements as some of the lowest inference costs in the market
Get started at no cost
All new sign ups get $10 of free usage on OctoAI
Frequently asked questions
Don’t see the answer to your question here? Feel free to reach out so we can help.
OctoAi is an efficient, customizable, and reliable platform for GenAI inference, so you can build and scale your production applications. The OctoAI compute service an efficient serverless compute layer to run their choice of OSS, fine-tuned, or custom models. OctoAI solutions are built on the OctoAI compute service.
At sign up, you get $10 of free credit, which doesn't expire. You can enter your credit card at any time and pay for your use at the end of each month. Free credits are always used before any credit card charges apply.
We do not have a generalized workflow builder. But, please review some of our demos to see examples of building pipelines from various models to create GenAI apps.
The SOC 2 Type II certification provides independent validation of these processes and safeguards. We do not persist the inputs, outputs, nor intermediate computations of your inferences, except for runtime logs that you choose to expose in your container. For encryption in transit, we ensure that all connections from customer to the OctoAI compute service require TLS, without you having to manage TLS certifications yourself. We also use encryption at rest for any data that we write to disk.
No. Your data is never used for training purposes. See more details about our SOC 2 compliance and data policies.
Start building with ease in minutes using OctoAI
Our mission at OctoAI is to make AI sustainable and accessible so that developers are liberated to build the next generation of intelligent applications. Sign up and enjoy the freedom to choose your model, infrastructure, and deployment templates.