Multi-Model AI:
Credits vs. Tokens.

What are Credits?

Credits are the standard unit of measure for your AI activity within the Secure AI platform. Every user is allocated a specific number of credits, which can be shared across your entire company team. This approach ensures your organization can provide secure AI access to everyone; it allows for flexibility where team members who perform lighter tasks balance out those who are “power users” of the technology.

How does the credit system work?

Because not every team member uses AI the same way, our credit system is designed to measure usage fairly across your platform. Credits automatically reset to your standard amount on the first day of every month, which means they do not roll over from one month to the next.

How are credits calculated?

Credit consumption is determined by two main factors combined into one formula. First, we calculate the tokens—the data units processed—based on the specific Language Model (LLM) you have selected, as different models have varying pricing for input and output. Second, we account for platform actions, such as file uploads, web scraping, or API calls.

What impacts the cost of a chat?

The complexity of your interaction is the primary driver of credit usage. A typical, secure AI chat session generally costs between 1 and 30 credits, depending on three key variables: the length and complexity of your messages, the number of messages exchanged, and any additional actions taken, such as uploading files to the chat.

Understanding usage in practice

When summarizing a standard, single-page document, you can expect to use between 1 and 12 credits. The exact amount depends on the LLM selected and the complexity of the document’s word structure and length. While it is nearly impossible to predict the exact token usage of a prompt before it runs, these estimates help provide a general guideline for your daily activities.

Talk to your Tech Minded representative for pricing.

Credits give you flexibility. 
Your organization's pool spreads the wealth.

Tech Minded AI is sold in packages intended to be shared across the users in your organization. In doing it in this way, you give everyone a solution, but without the normal costs of doing so. Credits are calculated in real time -- more expensive models, or faster modes, cost more credits. Simpler requests, and less expensive models use less credits.

Every organization is different, and usage varies from organization to organization. Below is guidance on what number of people generally works within each package.

• Intro Package: 30,000 credits (typically for 5 or less users)
• Starter Package: 100,000 credits (typically for 6 to 49 users)
• SMB Package: 250,000 credits (typically for 50 to 99 users)
• Business Package: 750,000 credits (typically for 100 to 149 users)
• Professional Package: 1,500,000 credits (typically for 150+ users)
• Additional blocks of 250,000 as needed)

Credit Usage is dependent on a verity of factors, most prominent being the LLM selected, and the number of AI Tokens used. It is nearly impossible to determine the exact number of AI Tokens a prompt will use, however, estimations can be made based on previous token measurements provided by the LLM. As people have more success in using AI, and find it useful, usage tends to increase over time.

Talk to your Tech Minded representative for pricing.

Every message, every time.

The AI platform is evaluating for each message, not just once for the conversation. Within a single conversation, a quick follow-up question might go to a fast, lightweight model, while a detailed coding request in the very next message gets routed to a heavyweight. You don't have to do anything -- it just works.

Flexibility

Auto doesn't lock you in. Every message is independent. There's no commitment, no state to reset. You can:

• Switch away at any time -- change to a specific model mid-conversation whenever you want
• Switch back -- return to Auto on the next message and it picks up right where it should
• Mix and match -- use Auto for most messages and manually select a model when you have a preference

What makes Auto worth using

You'll see for yourself when you start to use it, Auto is one of the AI platform's best features — and it saves you money. And there's no extra charge for using it.

• Use fewer credits without compromising quality. Auto matches each task to a model that delivers a great result -- and nothing more expensive than necessary. Simple questions go to efficient models, so you stop spending premium credits on tasks that don't need premium capability. The quality stays high; the credit usage goes down.
• Better answers. Each task gets matched to a model that's actually good at that kind of work -- whether it's writing code, generating images, analyzing data, or answering a quick question.
• Speed where it matters. Lightweight requests get fast models. You're not waiting three seconds for "what does this acronym mean?" just because you had a powerful model selected from an earlier task.
• Zero maintenance. As new models are added and the routing improves over time, you benefit automatically. No need to stay current on which model is best for what.