AI Studio

Hyperstack's AI Studio gives you serverless inference on a catalog of text and image models: send requests through an OpenAI-compatible API, test models in the interactive playgrounds, and ground answers in your own documents with knowledge bases. You pay only for what you use, per token for text models and per image patch for image generation, with no model to deploy. To serve a model on GPUs reserved for you instead, use Dedicated Inference. Standard API access and integrations connect AI Studio to your existing tools and frameworks.

Topics

Getting Started

Choose your path and start running models or building with the API in AI Studio.

Playground

Test text and image models interactively, with parameter tuning and side-by-side comparison.

Dedicated Inference

Deploy an open-weight model on GPUs reserved for you and get a private, API key-protected endpoint.

Models

The models available for inference, by modality, with pricing.

Knowledge Bases

Index your own documents so the Text Playground can answer from them and cite the passages it used.

Integrations

Connect AI Studio to popular developer tools, editors, and AI frameworks.

Billing

Usage pricing and cost transparency for AI Studio.