Find and select a model

List the models available to your credential and choose a calling method based on the task and model capabilities.

Prerequisites

Prepare a personal access token or service account API Key with Genesis permissions. See Access credentials for credential selection and permissions.

Call sequence

  1. List callable models using the credential you will use for inference. Filter for chat, embedding, or reranking models as needed.

  2. Review the candidates’ types, capabilities, and prices, and select a model that supports the required calling method.

  3. Keep the selected model’s calling identifier and continue to the corresponding generation or reranking task.

API operations

Task

API operation

When to use it or what to check

Select an available model

List callable models

Use the actual inference credential to check model identifiers, capabilities, and prices.

Confirm the result

Confirm that the selected model appears in the result for the current credential and supports your task. Use its calling identifier in the model request.

Limitations and notes

The callable model list is specific to the current credential. Browsing a model catalog does not confirm permission to call a model.

Next steps

Last updated on