Whatever message this page gives is out now! Go check it out!
Create a chat model
Last update:
May 18, 2026
The chat model is the fundamental interface for interacting with large language models (LLMs). It is a stateless engine: it accepts a sequence of messages (via a simple string in
.chat()) and returns a response. It does not maintain conversation history or tools by itself.Use
ChatModel() with a configuration struct. The table below lists the parameters you need most often to run your first call. For the full parameter matrix (all providers), see Build with AI.Syntax
chatConfig = {
PROVIDER : "openAi",
APIKEY : "#application.apiKey#",
MODELNAME : "gpt-4o-mini",
TEMPERATURE : 0.7
};
chatModel = ChatModel(chatConfig);
Common parameters (quick reference)
| Param name | Type | Description |
|---|---|---|
provider | String | Provider of the model (required). Example: "openai". |
baseUrl | String | Base URL for the API endpoint (required or defaulted per provider). |
apiKey | String | Authentication key for cloud APIs (not used by Ollama). |
modelName | String | Model identifier (required). Example: "gpt-4o-mini". |
temperature | Number | Randomness of the output (optional). Typical: 0.7. |
maxTokens | Number | Maximum tokens to generate (optional). |
timeout | Number | Seconds to wait for a response (optional). |
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Share additional feedback to help us improve.
0/255
|
