Kimi-K2.6

Kimi-K2.6

High-performance general-purpose model built for long context, reasoning, and real-world assistant tasks.

Long Context Focus. Designed to handle very large inputs and long conversations without breaking down. Strong at document-heavy workflows and multi-step interactions.

Strong Reasoning. Good performance on math, coding, and structured problem solving - competitive with larger models in many cases.

Generalist Model. Works well across chat, writing, coding, and analysis without needing special modes or complex prompting.

Production Ready. Stable outputs and consistent behavior, suitable for real-world applications and user-facing systems.

Why pick it for Norman AI?

Kimi-K2.6 is a strong all-around model with a focus on long context. Use it when you need one model that can handle large documents, extended conversations, and solid reasoning without going into very large (and expensive) model territory.

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": "kimi-k2.6",
        "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": "kimi-k2.6",
        "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": "kimi-k2.6",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)