Model Configurations

The model object in your Agent configuration defines which language model processes the conversation. It is a required field when creating or updating an Agent.

Schema

1 {
2   "model": {
3     "provider": "openai",
4     "model": "gpt-4o-mini",
5     "system_prompt": "You are a helpful AI assistant.",
6     "temperature": 0.8,
7     "max_tokens": 3500,
8     "tools": []
9   }
10 }

Parameters

Property	Type	Required	Description
`provider`	`string`	✅	LLM provider (see supported providers below)
`model`	`string`	✅	Model ID from the provider (e.g. `gpt-4o-mini`)
`system_prompt`	`string`	✅	The system instruction given to the model
`temperature`	`number`	✅	Randomness level — `0.0` to `2.0`, default `0.8`
`max_tokens`	`number`	✅	Max tokens per response, default `3500`
`tools`	`array`	❌	List of tool IDs to attach to this model, default `[]`

Supported Providers

Provider	`provider` value
OpenAI	`openai`
Anthropic	`anthropic`
Google Gemini	`google`
Groq	`groq`
DeepSeek	`deep-seek`