model

The model block configures an LLM provider and model.

Syntax

model <name> {
  provider    = <string>
  model_name  = <string>
  api_key     = <string>  // optional
  base_url    = <string>  // optional
  temperature = <float>   // optional
}

Fields

Field	Type	Required	Description
provider	str	Yes	LLM provider: "openai", "anthropic", or "google"
model_name	str | model	Yes	The model identifier (e.g., "gpt-4o", "claude-sonnet")
api_key	str | null	No	API key for the provider (overrides environment variable)
base_url	str | null	No	Custom base URL for the provider endpoint
temperature	float | null	No	Sampling temperature (0.0 – 1.0)

Supported providers

Provider	Generated class	Python package
"openai"	ChatOpenAI	langchain-openai
"anthropic"	ChatAnthropic	langchain-anthropic
"google"	ChatGoogleGenerativeAI	langchain-google-genai

The compiler automatically adds the correct package to pyproject.toml based on which providers you use.

Examples

OpenAI

model gpt4 {
  provider    = "openai"
  model_name  = "gpt-4o"
  temperature = 0.7
}

Anthropic

model claude {
  provider    = "anthropic"
  model_name  = "claude-sonnet-4-20250514"
  temperature = 0.5
}

Google

model gemini {
  provider    = "google"
  model_name  = "gemini-2.0-flash"
}

Generated output

model gpt4 {
  provider    = "openai"
  model_name  = "gpt-4o"
  temperature = 0.7
}

Compiles to:

from langchain_openai import ChatOpenAI

gpt4 = ChatOpenAI(model="gpt-4o", temperature=0.7)  # main.oc:1