Ask Sage Tokens
In this section, we will provide a comprehensive overview of tokens and their usage within the Ask Sage platform. Understanding the concept of tokens is crucial, as they serve as the primary means of accessing the platform and function as its currency.
Table of contents
What is a Token?
A token in terms of Generative Artificial Intelligence (GenAI) refers to the count of characters or words that are vectorized and processed by the model. Tokens can be as short as one character or as long as one word, depending on the language and the specific implementation of the model. For example, in English, common words like “cat” or “dog” are typically single tokens, while punctuation marks and spaces are also treated as individual tokens. The model uses these tokens to generate, understand, and manipulate text.
So in the context of Ask Sage, users are allocated tokens based on their subscription plan, which they can use to interact with the platform’s features, such as training models, and making inferences.
What are Ask Sage Tokens?
Ask Sage tokens are unique in that they are model-agnostic and serve as the central currency for interacting with the Ask Sage platform. These tokens enable users to access and utilize any model on the platform without additional effort or extra costs. Consequently, Ask Sage tokens are consumed based on the type of operation performed, such as training a model or making an inference. It is important to note that each model consumes tokens differently, depending on its complexity and the amount of data processed.
Also, Ask Sage tokens are divided into two categories:
-
Inference Tokens -
Training Tokens
Ask Sage provides users with a seamless experience and flexibility by offering a unified
tokensystem that can be used across all models on the platform. This simplifies the process of managingtokensand ensures a consistent user experience across different models as it pertains totokenusage.
Ask Sage Inference Tokens
Ask Sage Inference Tokens are used to make predictions or inferences using the models available on the platform. These tokens are consumed when users submit prompts, use the plugins/agents to generate responses, or interact with the models in any way that requires processing text data. The consumption of inference tokens is based on the complexity of the model and the amount of data processed during the inference process.
Inference tokens are limited by the user’s subscription plan, and users can monitor their token usage through Token/Subscription window in the Ask Sage platform. This feature allows users to track their token consumption and manage their usage effectively.
Users can purchase additional
inference tokensif they exceed their allocated limit or require moretokensfor their tasks. This flexibility ensures that users can continue to use the platform without interruptions or restrictions.
Ask Sage Training Tokens
Ask Sage Training Tokens are used to create training datasets in the Ask Sage platform. These tokens are consumed when users upload data to a dataset. Note that training tokens cost less than inference tokens, as training tokens are used to create datasets and not to make predictions. The consumption of training tokens is based on the size of input data that is uploaded to the platform for training purposes.
Similar to inference tokens, training tokens are limited by the user’s subscription plan, and users can monitor their token usage through the Token/Subscription window in the Ask Sage platform. This feature allows users to track their token consumption and manage their usage effectively.
Token Refill and Subscription Plans
Ask Sage offers users the flexibility to refill their tokens or upgrade their subscription plans based on their requirements. Users can purchase additional tokens or switch to a higher subscription tier to access more tokens and features. This ensures that users have the resources they need to work efficiently and effectively on the platform.
Additionally, Ask Sage tokens replenish automatically on the first day of each month, providing users with a fresh allocation of tokens to use for the month. This feature ensures that users can continue to use the platform without interruptions and plan their tasks accordingly.
Tokens do not transfer from one month to another, so it is essential for users to utilize their tokens effectively within the allocated time frame.