Kimi K3.1 Pro 개요

stream = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[{"role": "user", "content": "Design a task queue with retry handling."}],
    reasoning_effort="low",
    max_completion_tokens=8192,
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in stream:
    if chunk.usage is not None:
        print("\nUsage:", chunk.usage)
    if not chunk.choices:
        continue

    delta = chunk.choices[0].delta
    reasoning = getattr(delta, "reasoning_content", None)
    if reasoning:
        # Render reasoning separately from the final answer.
        pass
    if delta.content:
        print(delta.content, end="", flush=True)

import json

messages = [{"role": "user", "content": "Check the delivery status of order A100."}]
tools = [{
    "type": "function",
    "function": {
        "name": "get_order_status",
        "description": "Get the delivery status of an order",
        "parameters": {
            "type": "object",
            "properties": {"order_id": {"type": "string"}},
            "required": ["order_id"],
            "additionalProperties": False,
        },
    },
}]

response = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=messages,
    tools=tools,
    reasoning_effort="low",
    max_completion_tokens=8192,
)
message = response.choices[0].message
messages.append(message.model_dump(exclude_none=True))

if message.tool_calls:
    for call in message.tool_calls:
        arguments = json.loads(call.function.arguments)
        # Example result; validate arguments and query your order service in production.
        result = {"order_id": arguments["order_id"], "status": "shipped"}
        messages.append({
            "role": "tool",
            "tool_call_id": call.id,
            "content": json.dumps(result),
        })

    final = client.chat.completions.create(
        model="kimi-k3.1-pro",
        messages=messages,
        tools=tools,
        reasoning_effort="low",
        max_completion_tokens=8192,
    )
    print(final.choices[0].message.content)
else:
    print(message.content)

response = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[
        {"role": "system", "content": LONG_STABLE_CONTEXT},
        {"role": "user", "content": "List three key findings from the reference material."},
    ],
    reasoning_effort="low",
    max_completion_tokens=8192,
    extra_body={
        "prompt_cache_options": {"mode": "implicit", "ttl": "1h"}
    },
)
print(response.usage)