How Namirasoft Inference Works

Set up an AI model once, then use it across your Namirasoft applications.


Add a model, choose how it connects, set spending limits, and track every token, all from one place.





Step 1: Create a Namirasoft Account


Start with a Namirasoft account

All you need to begin is a Namirasoft account. It gives you access to the Namirasoft Inference console and every Namirasoft application.

 

 

Once you are signed in, the console opens and you are ready to add your first model.




Step 2: Add a Model


Create and name your model

In the console, add a model and choose which AI model it runs.

 

  • Add a new model
  • Enter a name for the model
  • Choose a provider: Claude, ChatGPT, DeepSeek, or Namirasoft Squirrel
  • Select a model from that provider

 

The model now has a name and an AI model assigned. Next, choose how it connects.




Step 3: Choose How It Connects


Pick a connection method

Decide how Namirasoft Inference connects to the AI model. Choose one of two methods:

 

  • Namirasoft-Provided Access: use the model right away, with no key required.
  • Your Provider Account: add your own provider API key so the provider bills you directly. Learn how to get your API key.

 

Note: With your own provider account, Namirasoft adds only its fee. See Pricing for how each method is charged.

 

The connection method is set. Next, set spending limits.


View Pricing



Step 4: Set Cost Limits


Cap spending, then save

Set optional spending limits in US dollars. When a limit is reached, the model stops until that period resets, so it never costs more than you set.

 

  • Set a limit per run?RunA single model request and its response. and per chat?ChatOne conversation, which can include multiple runs.
  • Set limits per day, per week, and per month
  • For example, a $5.00 daily limit stops the model for the rest of the day once reached
  • Click Apply to save the model

 

The model is created and appears in your model list, ready to use across your applications.




Step 5: Use the Model in Your Applications


Select the model where you work

The saved model is available across Namirasoft applications.

 

  • Open an application such as Namirasoft Expert
  • Select the model you created
  • The application now runs on that model

Explore Namirasoft Expert



Step 6: Monitor Usage


Track tokens and cost over time

Return to the console at any time to see how each model is used.

 

  • See input and output tokens
  • See the cost and the amount paid
  • View totals by day, week, month, and all time

 

Use these insights to adjust limits or switch models as your needs change.



Ready to configure your first model?



How It Works FAQs


Common questions about setting up and using AI models in Namirasoft Inference.


1. How do I add an AI model?

You create a model by choosing a provider, selecting a model, and giving it a name. It then becomes available across your Namirasoft applications.

2. What is the difference between Namirasoft-Provided Access and Your Provider Account?

With Namirasoft-Provided Access, Namirasoft connects you to the model with no setup. With Your Provider Account, you add your own API key and the provider bills you directly. See Pricing for how each option is charged.

3. Can I control how much a model spends?

Yes. Every model can have spending limits per run, per chat, per day, per week, and per month, so usage always stays within budget.

4. What usage can I see?

You can see input and output tokens, the underlying cost, and the amount paid, broken down by day, week, month, and all time.

5. Where can I use a model after I configure it?

A configured model is available across Namirasoft applications, such as Namirasoft Expert.

6. Can I run more than one model?

Yes. You can configure as many models as you need, each with its own connection, spending limits, and usage tracking.



Still Have Questions or Ready to Get Started?