Frequently Asked Questions
Have questions about Namirasoft Inference? This section provides clear and concise answers to help you better understand the service. Whether you are just getting started or exploring advanced features, these FAQs are here to support your experience.
Home Page FAQs
Answers to common questions about Namirasoft Inference.
1. What is Namirasoft Inference?
Namirasoft Inference is a unified orchestration layer for LLM calls. It gives your application one place to connect AI models, decide how requests are handled, and define the logic, safeguards, context, budgets, and other components around each execution.
2. Which AI models are supported?
Namirasoft Inference supports 500+ AI models from 80+ providers, including leading models such as ChatGPT, Claude, Gemini, DeepSeek, and Grok, along with many more.
3. What is an inferencer?
An inferencer is anything that can answer an AI request. A Model answers the request directly, while inferencers such as Load Balancer, Failover, Race, Router, and Gateway determine how the request is handled and ultimately return a response.
4. How can I decide which model or inferencer handles a request?
You define the routing logic. You can send a request directly to a Model, distribute it across several inferencers with a Load Balancer, switch to another inferencer with Failover, use the first response with Race, or direct requests based on your rules with a Router.
5. Can I use more than one AI model in an execution?
Yes. An inferencer can call another inferencer, so you can combine models and execution components into a single flow. For example, a Load Balancer, Failover, or Race can work with multiple models, while a Router can direct different requests to different inferencers.
6. Can I change the AI model behind my application?
Yes. Your application calls the configured inferencer rather than being tied directly to a specific model. You can change the model or execution configuration in Namirasoft Inference without changing the AI integration in your application.
7. Can I control what happens before and after an AI model responds?
Yes. You can apply Guardrails to user prompts and AI output, validate and correct responses with Validators, use Rules to make execution decisions, provide context through Memory and Knowledge Bases, and apply other components around your models.
8. Can I manage conversation context across different AI models?
Yes. Memory keeps conversation context independently of the model being used. This allows you to change or route between models without losing the relevant conversation history.
9. Can I use my own API keys?
Yes. You can connect supported third party providers using your own API keys and use those credentials with your configured models. The connection is managed through Namirasoft Credential.
10. Can I use Namirasoft Inference with my own application?
Yes. You can integrate Namirasoft Inference into your own application and send AI requests through its API. For API reference, integration details, and documentation, visit the Namirasoft Inference API documentation.
11. How much does Namirasoft Inference cost?
Namirasoft Inference includes a free monthly allowance, with additional pricing options available depending on how you use the service. For the current free allowance and pricing options, see the Pricing page.
How It Works FAQs
Common questions about setting up and using AI models in Namirasoft Inference.
1. What is an inferencer?
An inferencer is the execution unit in Namirasoft Inference. Your application sends a request to an inferencer, and the inferencer determines how that request is processed and completed. A Model calls one AI model directly, a Load Balancer distributes requests, a Failover switches targets on failure, a Race keeps the first successful response, a Router chooses execution paths, and a Gateway wraps execution with additional processing.
2. How can I connect my own AI provider API key?
You add your provider API key through Namirasoft Credential, and the key value stays encrypted through Namirasoft Secret. Namirasoft Inference retrieves the credential securely when it executes a request, so your key never appears inside requests or application code.
3. How can I connect my application to Namirasoft Inference?
Your application connects through the Namirasoft Inference API. Any stack that can call an HTTP API works, including Node.js, React, and PHP applications, and the NPM and PHP SDKs cover the most common setups. The full reference is available in the Documentation.
4. How does a Load Balancer distribute requests?
A Load Balancer sends each request to one of its target inferencers. You define the targets, set a Weight for each one, and choose the Algorithm, Random or Round Robin. Traffic then spreads across your execution paths in the ratio you set.
5. What are Log Groups used for?
A Log Group collects the info and error logs of the entities you assign to it. When a request needs debugging, the logs show what happened at each entity during processing, so you can see exactly how a request was handled.
6. How does a Validator work?
A Validator checks whether an AI response matches the format you define, such as JSON, YAML, or XML. When validation fails, it either returns an error or calls the corrector inferencer you chose to fix the response, and the Retry Count limits how many correction attempts run.
7. How do Guardrails protect AI requests?
Guard Rails screen the user prompt, the AI output, or both. Rules cover unsafe content detection, PII protection, prompt injection detection, and your own custom rules, and the request stops with a clear error when a rule matches.
8. What is the difference between Conditions and Classifiers?
A Condition evaluates explicit properties of a request, such as its text, length, or tags, so routing follows the criteria you state directly. A Classifier reads the request and assigns it to the classes you define, so routing can follow meaning instead. Conditions can also check the classes a classifier assigns.
9. Will changing AI models remove previous conversation context?
No. AI models do not remember previous messages on their own. Namirasoft Inference keeps conversation context in Memory, independent of the model, so switching models keeps the stored context when Memory is attached.
10. Can I use multiple AI models for the same request?
Yes. A Load Balancer spreads requests across several models, a Failover tries them in order until one answers, and a Race calls them at the same time and keeps the first successful response. Any inferencer can be a target, so these patterns also combine.
Pricing FAQs
Find details about how pricing works in Namirasoft Inference.
1. What does Namirasoft Inference pricing cover?
Namirasoft Inference pricing covers your platform usage: the requests you send and the conversation memory you keep. AI models are billed separately, each with its own pricing. You either bring your own API key for a supported model, or use Namirasoft Squirrel.
2. What counts as a request?
A request is one input you send to Namirasoft Inference. A Load Balancer, Failover, or Race counts as a single request, even when it makes several calls.
3. What is conversation memory?
It is the prompts you send and the responses you receive, retained so your applications keep context across messages. Along with requests, it is what Namirasoft Inference pricing is based on.
4. Is AI model usage included in Namirasoft Inference pricing?
No. The AI models are governed and billed by their own provider, not by Namirasoft Inference. You bring your own API key for a supported model, or use Namirasoft Squirrel. Namirasoft Inference does not set or display these prices, it only links you to them. See provider API pricing or Namirasoft Squirrel pricing.
5. How do I configure my AI models?
You configure your AI models in the Namirasoft Inference app. Use Namirasoft Squirrel, or bring your own provider API key for a supported model.
6. Can I control AI costs?
Yes. You can set cost limits per run, per chat, per day, per week, and per month. When a cost limit is reached, further usage is restricted to your settings.
7. Can I change the AI models my applications use?
Yes. You can configure and change supported AI models at any time to fit each application.
8. Do I only pay for what I use?
Yes. Namirasoft Inference uses usage based pricing, and no credit card is needed to start. You pay only for requests and conversation memory beyond your monthly free allowance. See the pricing table for the rates.