LLM and model settings
An agent's behavior depends on two sets of model settings:
- The Models card in the agent's Advanced mode Settings panel, where you choose which model connections the agent uses.
- The connection itself, created in Settings > Connectivity, where you enter the provider URL, key, model name, and sampling settings.
This page explains each setting — what it controls, when to change it, and a safe starting point. For the steps to select a model on an agent, see Select AI models; for the steps to create a connection, see Add an LLM integration.
The Models card
The Models card lists one row per model role. Each row is a dropdown of the matching connections from Settings > Connectivity; the placeholder reads None until you pick one. Selecting a connection here attaches it to this agent — it does not create or edit the connection.
| Row | What it does | When you set it |
|---|---|---|
| LLM | The language model that understands customer messages and generates replies. | Always — the agent does not run without it. |
| MCP Tools | Tools provided by Model Context Protocol servers. You can select more than one connection. | When the agent calls tools from an MCP server. |
| OpenAPI Tools | HTTP tools generated from an OpenAPI specification. You can select more than one connection. | When the agent calls tools created from an OpenAPI spec. |
| Visual Language Model | A model that combines visual understanding with text processing. | When the agent must interpret images. |
| Text-To-Speech | Converts the agent's replies to spoken audio. You can select more than one connection. | Voice agents. |
| Speech-To-Text | Converts the caller's speech to text. | Voice agents. |
| Skills Embedder Model | An embedding model that turns text into vectors. | When the agent's skills need embeddings. |
| Transcription model | Converts audio recordings into text. | Call Analytics agents. |
The rows shown depend on the agent type. A Call Analytics agent shows the Transcription model row in place of the live speech rows; the Visual Language Model row appears only for agent types that support images. After you change a selection, click Save, then restart the agent — Advanced mode does not restart it on save.
LLM is the only required row. Without a selected LLM the agent cannot start. The other rows are optional and depend on what the agent does.
LLM connection settings
The LLM connection is created under AI Models > Large Language Model (LLM) in Settings > Connectivity. It connects any model behind an OpenAI-compatible API. These are the fields you set on the connection.
| Field | Required | What it does | When to change it |
|---|---|---|---|
| Name | Yes | A label for the connection, unique within your tenant. | Set once. Use a name that identifies the provider and model, for example OpenAI gpt-4o prod. |
| API URL | Yes | The OpenAI-compatible base URL of the provider. | When you switch providers or endpoints. Use the base URL — for OpenAI, https://api.openai.com/v1. |
| Access Token | Yes | The API key issued by the provider. Stored as a secret and shown masked after saving. | When the key is rotated or revoked. Type the new value over the masked field to replace it. |
| Model Name | Yes | The model identifier exactly as the provider expects it, for example gpt-4o. | When you move to a different model, or your provider deprecates the current one. |
| Temperature | Yes | How varied the model's replies are. See Temperature. | Lower for fact-based agents; raise only if replies feel too rigid. |
| JSON params | No | Additional sampling parameters as a JSON object, sent to the provider with each request, for example {"max_tokens": 1024}. Defaults to {}. | Only when your provider documents a parameter you need. Leave empty if unsure. |
After you save the connection, the portal tests it by sending a real request to the model, and the connector card shows a green status dot when the test succeeds. See Check integration status.
Temperature
Temperature controls how varied the model's output is: low values keep replies focused and repeatable, high values make them more varied and less predictable.
| Value | Model behavior |
|---|---|
| 0.0 | Accurate and deterministic. Best for support agents and anything fact-based. |
| 0.7 | Balanced between accuracy and variety — works for most conversational agents. |
| 1.0 | Highly varied and less predictable. Suited to brainstorming and marketing copy. |
Start with a low temperature (0 to 0.3) for customer-support agents and raise it only if replies feel too rigid. Use the range your model provider documents.
Speech model settings for voice agents
A voice agent needs two speech connections in addition to its LLM: one to transcribe the caller and one to read replies aloud. Create them in Settings > Connectivity, then select them in the Speech-To-Text and Text-To-Speech rows of the Models card.
Speech-to-text (STT) — created under AI Models > Speech-to-text (STT).
| Field | Required | What it does |
|---|---|---|
| API URL | Yes | The OpenAI-compatible base URL of the speech-to-text service. |
| Access token | No | The API key issued by the provider. Stored as a secret. |
| Type | No | The transcription engine, for example whisper or local_whisper. |
| Model name | No | The transcription model identifier the provider expects. |
| Certificate | No | A client certificate, when the service requires one. Stored as a secret. |
Text-to-speech (TTS) — created under AI Models > Text-to-speech (TTS).
| Field | Required | What it does |
|---|---|---|
| API URL | Yes | The OpenAI-compatible base URL of the text-to-speech service. |
| Access token | No | The API key issued by the provider. Stored as a secret. |
| Type | Yes | The synthesis engine, for example open_voice, azure_speech, or eleven_labs. |
| Region | No | The provider region, when the service uses one. |
| Voice | No | The voice the agent speaks in. |
| Speech speed | No | The speaking rate. |
Speech-to-text connections are health-checked and show a status dot; text-to-speech connections are not, so confirm one works by placing a test call. The SIP voice channel uses these speech connections; the Twilio channel uses Twilio's built-in speech and does not need them. For the full field reference and setup steps, see Add speech integrations for voice agents.
Related pages
- Create an Agent in Advanced Mode — select model connections on the agent's Models card
- Connectivity — create and test the model connections
- SIP — voice calls that use the speech connections
- Twilio — voice calls with built-in speech