Skip to content

Models

The Models page in the PinionAI Studio interface is dedicated to defining and managing the Large Language Models (LLMs) available to your agents. This allows for fine-grained control over model versions, providers, local hosting configurations, cost tracking, and rate limits.

Prerequisites

Before you can manage Models, ensure the following conditions are met:

  1. You must be logged into the application.
  2. Your user role must have the necessary permissions (owner, admin, editor, or models).
  3. You must have an Account selected from the sidebar.

Page Overview

The Models page is divided into two main sections:

  1. Add Model: An expandable form for creating new model configurations.
  2. Models List: A list of existing models associated with the selected account and agent, providing details on status, provider, and capabilities.

Creating a New Model

To create a new model:

  1. Navigate to the Models page.
  2. Expand the "New Model" section.
  3. Fill out the configuration fields described below.
  4. Click Create Model.

OR:

  1. Click on AI Suggest Configuration to have AI build a base configuration based upon user input.

Configuration Fields

Basic Information

  • Name: A unique name for the model configuration (e.g., gemini-3.1-flash-lite).
  • Model Value: The specific identifier required by the provider (e.g., gemini-3.1-flash-lite, gpt-4o).
  • Status: Toggle to enable or disable the model.
  • Agent(s): Associate this model configuration with specific agents. Select "All" to make it globally available within the account.
  • Provider: The model service provider (e.g., google, openai, anthropic, deepseek, grok, meta, ollama, openai-compatible, mistral).
  • Model Type: Defines the hosting environment (cloud, local, ip, huggingface, custom).

Connection & Security

  • Connector: Select a Connector that provides the necessary API keys or Service Account credentials for this model.
  • Protocol: The communication protocol (http, https, grpc websocket).
  • Base URL: The URL or path for local or IP-based models (e.g., 10.0.0.6 or a variable like {{var.ollama_local_ip}}for local Ollama).
  • Variable for Local Base URL: Please note that you can use variables to decide where to connect to your local model (e.g., {{var.ollama_local_ip}}).
  • Version/Parameter String: Optional release or version string of the model. (e.g., api/generate for local Ollama)
  • Port: The port number for IP-based models. (e.g. 11434 for Ollama)
  • SSL Verify: Toggle whether to verify SSL certificates for custom endpoints.

Advanced Configuration

  • Custom Headers (JSON): Additional HTTP headers required for custom API endpoints.
  • Model Config JSON: Flexible storage for provider-specific configurations.
  • Model Params JSON: Additional model parameters

Listing and Managing Models

The Models List section displays all models associated with the selected criteria:

  • Filtering: The list respects the agent selection in the sidebar.
  • Details: Expanding a model entry reveals its full configuration, including connection details, costs, and limits.
  • Edit: Click the edit icon to modify any aspect of the model configuration.
  • Delete: Remove a model configuration from the account.

Usage Examples

Example 1: Google Gemini (Cloud)

  • Name: gemini-3.8-flash
  • Model Value: gemini-3.8-flash
  • Provider: google
  • Type: cloud
  • Connector: gemini-service-account
  • SSL Verify: True

Example 2: Local gemma4:12b (Ollama)

  • Name: gemma4:12b
  • Model Value: gemma4:12b
  • Provider: ollama
  • Type: local
  • Protocol: http
  • Base URL: 10.0.0.24 or use a variable to access a local model {{var.ollama_local_ip}}
  • Version/Parameter String: api/generate
  • Port: 11434
  • SSL Verify: True

Example 3: OpenAI GPT-4o

  • Name: gpt-4o
  • Model Value: gpt-4o
  • Provider: openai
  • Type: cloud
  • Connector: openai-api-key
  • SSL Verify: True

Important! - Add Models to Codes

Note: Codes controls selection lists in the PinionAI Studio admin interface. To make a selection from a list, you may also need to add the model into Codes so it can be selected. Match the model with the name.

Codes Example 1: Google Gemini (Cloud)

Type: model Name: gemini-3.8-flash Value: gemini-3.8-flash Filter: google

Codes Example 2: Local gemma4:12b (Ollama)

Type: model Name: gemma4:12b Value: gemma4:12b Filter: ollama