Skip to main content

Models

Refreshes every 2 minutes
Live data

The model table on this page loads live Hyperstack data from the AI Studio catalog each time you open the page. Learn how these docs stay accurate.

SourceList base models APIRefreshesEvery 2 minutes

The models available for inference in AI Studio, by modality, with pricing and where to find them.

Hyperstack AI Studio provides a catalog of text and image models that you can use for inference through the playgrounds and the API. This page lists the available models by modality, explains how they are priced, and shows where to find them in AI Studio.

Models are served through third-party provider API integrations and are listed with their prices on the Inference page in AI Studio. Because these models are provided by external services, AI Studio cannot guarantee continued availability, and access may be revoked at any time if a provider changes or removes support for a model. Pricing is also subject to change and may be updated by the provider at any time. Requests may be processed by external providers in order to fulfill your request, and usage is subject to the availability, reliability, and data-handling practices of those providers.

Model Modalities​

Hyperstack AI Studio offers a range of models spanning multiple modalities:

  • Text-to-Text – Generate text from text inputs, for tasks such as chat, summarization, reasoning, and code generation. Use them in the Text Playground.
  • Image-to-Text – Also called vision-language models. Generate a text response from an image and a text prompt, such as describing an image or answering questions about it. Use them in the Text Playground by attaching an image to your message.
  • Text-to-Image – Generate images from text prompts, for visuals such as illustrations, product mockups, and creative assets. Use them in the Image Playground.
  • Image-to-Image – Transform or edit existing images using an input image and an optional prompt, for workflows such as style transfer, image enhancement, and guided edits. Use them in the Image Playground.

Available Models​

The table below reads live data from the AI Studio catalog through the List base models API, so new models and availability changes appear here as they happen. It loads the latest catalog each time you open the page, and the catalog data refreshes every 2 minutes. Search by model name, or filter by modality, availability, and context length. The value in the Model column is the identifier you pass as model in an API request.

Loading the model list…
Availability Varies

Models are added and removed on an ongoing basis, and a model that is available now can become unavailable later. The table above reflects the catalog at the time you loaded this page.

For the models you can run right now, with their pricing and last health check, see the Models tab of the Inference page in AI Studio, or the Vision Models tab for image generation models.

Viewing Models​

The Inference page in AI Studio lists every model you can run right now, with its current price, on two tabs:

  • Models: text-to-text and image-to-text models, with the cost per 1 million input and output tokens.
  • Vision Models: image generation models, with the cost per 16×16 patch.

Each row also shows the model's modality and when it was last health-checked. Search by model name or filter by modality to narrow the list, and look for the Trending badge on the three most-used models on each tab.

Inference page, Models tab, listing each model with its modality, input and output price per 1 million tokens, and last health check, with a Trending badge on the most-used modelsInference page, Models tab, listing each model with its modality, input and output price per 1 million tokens, and last health check, with a Trending badge on the most-used models

Pricing​

Models are billed through AI Studio and appear in its unified billing system.

Pricing depends on what the model generates, not on whether it processes images:

  • Text-to-Text and Image-to-Text Models generate text and are billed per token. Image-to-text models are vision-language models: they accept an image as input, which is included in your input tokens, and return a text response.

    • Cost per 1 million input tokens
    • Cost per 1 million output tokens

  • Text-to-Image and Image-to-Image Models generate images and are billed per patch.

    • Cost per 16×16 patch, where 1 patch = 256 pixels (a 16×16 pixel region) of generated image output. See the Vision Models tab for the most up-to-date per-model pricing.

Pricing is subject to change. For the most up-to-date pricing, refer to the Models tab in AI Studio. For more details on billing within AI Studio, click here.

On this page