> ## Documentation Index > Fetch the complete documentation index at: https://explore.airia.com/llms.txt > Use this file to discover all available pages before exploring further. # 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 ***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 prepare models for use in Airia agents. To add a model to a project: 1. Select the desired model 2. Review the information 3. Select **Add** 4. Provide a friendly name to help you remember the model 5. Select if you'll use the Airia Universal Key or if you want to provide your own credentials for the model provider 6. Select the scope for model accessibility 7. Your model is now ready for use within Agents ## Editing a model You can revisit a model configuration at any time to edit the model display name, credential, prices(if using custom credential) and system prompt. Model configurations can be reviewed from either the Models page within a specific project or the Connected models page. ## 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. From any models page, select **Custom Model**. 2. Provide a display name, and select the model provider. 3. Add the model endpoint, and provide the model ID. Find supported provider endpoints below. 4. To get the most of Airia's consumption tracking, input the price charged by the provider for model usage. 5. Select the input type, and provide a system prompt \[Note: a system prompt is not required] The model ID field expects the value used for API processing (e.g., `claude-3-5-sonnet-latest`), not the display name. ### 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 Foundry | `https://{{Model-Friendly-Name}}.{{Region}}.models.ai.azure.com/chat/completions`
`https://{{resourceName}}.services.ai.azure.com/anthropic/v1/messages` | Supports both OpenAI-compatible and Anthropic endpoints
Model ID must be set to the `Model-Friendly-Name` value | | Azure (OpenAI) | `https://{{deploymentId}}.openai.azure.com`
`https://{{region}}.api.cognitive.microsoft.com` | Compatible with chat completions only
Model ID must be set to the `Model-Friendly-Name` value | | 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** — controls the creativity of a model. Higher values generate more creative responses; 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 system instructions to be included for the model request. * **Context settings** — date/time, timezone, user details, chat history, attachments, and user input controls that determine what runtime information the model can see. For a complete guide, see [AI Model Context Settings](/building-and-deploying-agents/agent-basics/ai-model-context).