> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sentivue.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM

> Providers that generate your workflow's responses

The language model reads the conversation so far and decides what the agent says next. It also evaluates your edge conditions, so it drives when the conversation moves from one node to the next.

Set your default model on [Model Configurations](/talk/configurations/inference-providers), and override it per workflow where you need something different. Credentials come from a [connection](/talk/configurations/connections).

## Supported providers

| Provider                                                     | Notes                                                    |
| ------------------------------------------------------------ | -------------------------------------------------------- |
| [OpenAI](/talk/configurations/providers/openai)              | Also covers voice and transcription                      |
| [Anthropic](/talk/configurations/providers/anthropic)        | Claude models. Language model only                       |
| [Gemini](/talk/configurations/providers/google-gemini)       | Gemini models via an AI Studio API key                   |
| [Vertex AI Gemini](/talk/configurations/providers/vertex-ai) | Gemini through your own Google Cloud project             |
| [Azure OpenAI](/talk/configurations/providers/azure-openai)  | Needs an endpoint URL. The model is your deployment name |
| [AWS Bedrock](/talk/configurations/providers/aws-bedrock)    | Authenticates with an access key pair                    |
| [Groq](/talk/configurations/providers/groq)                  | Also covers transcription                                |
| [OpenRouter](/talk/configurations/providers/openrouter)      | Routes to many models behind one key                     |
| [MiniMax](/talk/configurations/providers/minimax)            | Also covers voice                                        |
| [Sarvam](/talk/configurations/providers/sarvam)              | Indian languages. Also covers voice and transcription    |

<Note>
  A provider listed here as covering more than one service needs only **one** connection. Connect OpenAI once and it can drive the language model, the voice, and the transcriber.
</Note>

## Choosing a model

Each provider ships a list of models to pick from. If the one you want is not listed, enter its model name manually — the field accepts any model your account can reach.

Faster models cost less and reply sooner, which matters more in a voice conversation than in chat. A slow model is heard as a pause. Start with a fast model and move up only if the agent is not keeping up with your prompt.