Model Lifecycle Management

Model Library

The model library provides access to a large number of available models that you can leverage within your projects and Agents. This includes models from the leading providers and also includes Airia’s own fine tuned models.

Adding a model

Show Adding a Custom Azure ML Model to Your Project

Getting Started

1. _From your project dashboard or models library, select _New Model
2. _Click _Create Custom Model
3. _From the dropdown menu, select _Azure ML

Configuration Steps

1. Basic Information
   • Provide a display name for your model (this will be shown in your project)
   • Enter the model identifier number (or your choosing)
2. API Authentication
   • _Select _I have my own key
   • _Choose an existing credential (if applicable) or select _Create new credential
   • If creating a new credential, enter your Azure ML API key
   • Copy and paste your complete model endpoint URL*
3. Parameter Configuration
   • Manually add each parameter your model requires
   • For each parameter, specify:
     • Parameter name
     • Parameter data type
   • Click Add after completing all fields

Using Your Azure ML Model

1. In the Agent Studio, locate your model in the models panel (left side panel)
2. Drag and drop the model into your workspace
3. From the model card, select which specific Azure ML model you want to use
4. Adjust parameters as needed using the right side panel, which displays all available parameters you configured when adding the model.

Current Limitations
Please note the following limitations of our Azure ML integration:

• Currently supports Azure ML hosted models only
• Parameters are only supported in the parameters section
• No support for body input or nested parameters yet
• Only API key authentication is supported
• *URL query strings in the model endpoint are not supported
• APIs that require file uploads are not supported

We’re actively working to expand these capabilities in future updates.

You can search, review costs, and add models to an existing project or to a new project.

To add a model to a project:

1. Select the desired model
2. Review the information
3. Select Add to Project
4. Select the project you wish to add the model to
5. Provide a friendly name to help you remember the model
6. Select if you’ll use the Airia Universal Key or if you want to provide your own credentials for the model provider
7. Your model is now ready for use within Agents and prompt testing

Editing a model

You can revisit a model configuration at any time to edit the model display name, credential, prices or system prompt.

To edit a model:

1. Navigate to the Models

   page of the project

2. Select the model you would like to edit

3. Edit the desired settings

4. Save model changes

Adding a custom model

You can add models that Airia has not published when you bring your own key. This allows you to leverage existing accounts with model providers for the endpoints supported by Airia.

To add a custom model:

1. Navigate to the Models

   Library.

2. From the footer message, select Add a model

   .

3. Provide a display name, and select the model provider.

4. Add the model endpoint, and provide a model name. Find supported provider endpoints below.

5. To get the most of Airia’s consumption tracking, input the price charged by the provider for model usage.

6. Select the input type, and provide a system prompt [Note: a system prompt is not required]

Supported Endpoints

Provider	Endpoint	Notes
AI21	https://api.ai21.com/v1/chat/completions
Alibaba	https://dashscope-intl.aliyuncs.com/compatible-mode/v1/	Compatible with chat completions only
Anthropic	https://api.anthropic.com/v1/messages
AWS Bedrock	https://console.aws.amazon.com	Compatible with conversational models only
Azure AI Studio	https://{{Model-Friendly-Name}}.{{Region}}.models.ai.azure.com/chat/completions
Azure OpenAI	https://{{deploymentId}}.openai.azure.com/openai/deployments/{{Model-Friendly-Name}}/chat/completions
Cohere	https://api.cohere.com/v1/chat
Google	https://generativelanguage.googleapis.com/v1/models	Compatible with chat completions only
Mistral	https://api.mistral.ai/v1/chat/completions
OpenAI	https://api.openai.com/v1/chat/completions https://api.openai.com/v1/responses
Ollama	http(s)://{{SomeIpOrName}}:11434/api/chat
Perplexity	https://api.perplexity.ai/chat/completions
Replicate	https://api.replicate.com/v1/models/{{Model-Name}}/predictions
Together AI	https://api.together.xyz/v1/chat/completions
xAI	https://api.x.ai/v1/	Compatible with chat completions only
Custom	https://{{provider-domain}}/v1/	Specify any OpenAI compliant provider domain. Compatible with chat completions only.

Customizing an Agent model instance

Models can be configured in how they respond by setting several values in the sidebar when they are added to an Agent. These include

• Temperature - to control the creativity of a model. Higher values generate more creative responses, and lower values are more deterministic.
• System Prompt - added to a model during initial configuration. This is for visibility only and cannot be changed within the Agent.
• Prompt - any secondary or additional prompt message to be included with the model prompt.
• Include Context - provide context around the present day and time when sending messages to the model.