Model
Direct model execution.
A Model sends a request directly to the AI model you configure and returns the response. It is the smallest inferencer in Namirasoft Inference, and every larger pattern is built from it.
- Select from 80+ providers and 500+ AI models.
- Add your provider API key through Namirasoft Credential.
- Send requests directly to the selected model.
Set up a Model in the console
Give your application a direct connection to the model you choose, without putting provider credentials in your application code. Namirasoft Secret keeps your credential encrypted, while Namirasoft Credential delivers it securely when the Model needs it.
- Model Company and Model Name determine which model handles the request.
- Model API Key Credential ID selects the provider credential used for access.
- Create as many Models as you need, with no configuration cost.
See How Inference Works to explore how Models can work with other inferencers.
Expand what your Model can do
You can extend the Model with functionality for validation, cost management, conversation context, data cleanup, and debugging. Your application keeps calling the same endpoint, while each addition handles its specific responsibility on every request.
- A Validator makes sure every answer arrives in the format you expect, such as clean JSON.
- A Budget caps what the Model can spend per run, chat, day, week, or month.
- A Memory lets conversations remember earlier context, while a Wiper clears stored data according to your policy.
- A Log Group keeps a record of requests for debugging and review.
Select the functionality you need, and click Apply.
Every provider in the catalog
Choose from 80+ providers and 500+ models in the Model catalog.
What a Model changes for your application
A Model gives your application a configurable AI endpoint that you can change, monitor, and use as part of larger inferencer flows.
Connect to multiple models through a single API
Your application can connect to multiple models from different providers through the same Namirasoft Inference API, without building a separate integration for each provider.
Change models without code changes
Swap the Model Company or Model Name in the console, and every request that follows uses the new model. Your application code stays exactly as it is.
Build larger flows from your Models
A Model can become a target of a Load Balancer, a step in a Failover, a contender in a Race, or a route in a Router. The same Models you create here can be combined into more advanced execution flows.
Ready to build your AI execution flow?
Configure your first inferencer with help from our team.