How Inference Works
Configure AI models once, then use them across supported applications.
Set up a model in Namirasoft Inference and manage its access, cost, and usage from one place. Supported Namirasoft applications, such as Namirasoft Expert, run on the models you configure.
Approximate setup time: 2 to 5 minutes
Step 1: Create a Model
Start by creating a model
- Open the Namirasoft Inference console
- Go to Model
- Click Create to start a new model
Step 2: Choose the AI Model
Choose which AI model it runs
- Give the model a name
- Choose the model company: Claude, ChatGPT, DeepSeek, or Namirasoft Squirrel
- Select the AI model from that company
Step 3: Choose How It Connects
Choose how an external AI model connects
This choice applies to third party models such as Claude, ChatGPT, and DeepSeek. Namirasoft Squirrel runs on Namirasoft’s own models and needs no connection setup.
No setup
Namirasoft-Provided Access
Use the model right away, with no key required.
Your key
Bring Your Own Key
Add your provider API key in Namirasoft Credential, then return to Inference. Learn how to get your API key.
Step 4: Set Limits and Create
Set limits, then create the model
- For Bring Your Own Key, select the credential you added
- Set optional spending limits, from a single run up to a full monthWhen a limit is reached, the model stops and shows a message until that period resets, so it never costs more than you set.
- Click Apply to create the model
Set up your first model in minutes
How It Works FAQs
Common questions about setting up and using AI models in Namirasoft Inference.
1. Do I need an account to get started?
Yes. Sign up for a Namirasoft Account, which is free, to access Namirasoft Inference and every other Namirasoft application.
2. What is the difference between Namirasoft-Provided Access and Bring Your Own Key?
Both apply to external AI models such as Claude, ChatGPT, and DeepSeek. With Namirasoft-Provided Access, Namirasoft connects you to the model with no setup. With Bring Your Own Key, you add an API key from the provider and continue using your existing provider account. See Pricing for how each option is charged.
3. Do I need an API key for Namirasoft Squirrel?
No. Namirasoft Squirrel runs on Namirasoft’s own models, so no API key is required. An API key applies only to external models such as Claude, ChatGPT, and DeepSeek when you choose Bring Your Own Key.
4. 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. When a limit is reached, the model stops until that period resets, so it never costs more than you set.
5. Can I configure more than one model?
Yes. You can configure as many models as you need, each with its own connection, spending limits, and usage tracking.
6. Can I change models later?
Yes. You can update a model, adjust its limits, or switch to a different model at any time.
7. Do I need to configure a model for every application?
No. You configure a model once in Namirasoft Inference, and it becomes available across every supported Namirasoft application. There is no need to set it up again for each application.