Laguna-XS.2

Text

Laguna-XS.2

Compact, high-performance coding model built for fast and reliable software tasks.

Code First. Optimized for code generation, editing, and understanding across common programming languages. Strong at real-world dev workflows.
Small but Effective. XS-sized model designed to deliver solid coding performance with low latency and low compute cost.
Fast Iteration. Great for autocomplete, quick fixes, and tight feedback loops where speed matters more than deep reasoning.
Developer Friendly. Works well in IDE integrations, agents, and tool-calling setups without heavy infrastructure.

Why pick it for Norman AI?

Laguna-XS.2 is a practical coding model for production. Use it when you need fast, cheap, and reliable code generation — especially for assistants, copilots, or automated dev workflows.

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "laguna-xs.2",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "laguna-xs.2",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "laguna-xs.2",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)

View Docs