Guide pratique Kimi K3 : paramètres et matrice des trois API

from openai import OpenAI

client = OpenAI(
    base_url="https://aihubmix.com/v1",
    api_key="<AIHUBMIX_API_KEY>",
)

response = client.responses.create(
    model="kimi-k3",
    input="Answer in one word: capital of France",
)

# Observed response.output item types: ["reasoning", "message"]; text: "Paris"
# Multi-turn: input = [first user message] + response.output + [next user message]
# Observed second-turn answer with output items passed back: "Berlin"

from anthropic import Anthropic

client = Anthropic(
    api_key="<AIHUBMIX_API_KEY>",
    base_url="https://aihubmix.com"
)

response = client.messages.create(
    model="kimi-k3",
    max_tokens=4096,
    messages=[
        {"role": "user", "content": "Answer in one word: capital of France"}
    ],
)

# Observed response.content block types: ["thinking", "text"]; text: "Paris"
# Multi-turn: pass response.content back verbatim as the assistant message

response = client.responses.create(
    model="kimi-k3",
    input="Hello",
    tools=[{
        "type": "function",
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]},
    }],
    tool_choice="required",
)

# Observed output contains: {"type": "function_call", "name": "get_weather", "arguments": "{\"city\":\"London\"}"}

response = client.messages.create(
    model="kimi-k3",
    max_tokens=4096,
    tools=[{
        "name": "get_weather",
        "description": "Get weather for a city",
        "input_schema": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]},
    }],
    tool_choice={"type": "any"},
    messages=[{"role": "user", "content": "Hello"}],
)

# Observed: stop_reason "tool_use"; content contains a tool_use block calling get_weather

response = client.responses.create(
    model="kimi-k3",
    input="Paris is the capital of France. Extract the city name.",
    text={
        "format": {
            "type": "json_schema",
            "name": "extract",
            "strict": True,
            "schema": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]},
        }
    },
)

# Observed output text: {"city":"Paris"}

# usage of the second Responses call with identical long instructions
"input_tokens_details": {"cached_tokens": 1536}

# usage of the second Messages call with an identical long system prompt
"cache_read_input_tokens": 1536

response = client.responses.create(
    model="kimi-k3",
    input=[
        {"role": "user", "content": "Write a haiku about the sea."},
        {"role": "assistant", "content": "Waves fold into foam,"},
    ],
)

# Observed continuation: "salt hangs in the air— / moon pulls the tide home."

response = client.messages.create(
    model="kimi-k3",
    max_tokens=4096,
    messages=[
        {"role": "user", "content": "Write a haiku about the sea."},
        {"role": "assistant", "content": "Waves fold into foam,"},
    ],
)

# Observed continuation: "salt wind carries the gull's cry— / tide pulls ..."

input = [
    {
        "role": "user",
        "content": [
            {"type": "input_text", "text": "What is the dominant color of this image? One word."},
            {"type": "input_image", "image_url": "data:image/png;base64,<BASE64>"},
        ],
    }
]

# Observed output text: "Red"

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What is the dominant color of this image? One word."},
            {"type": "image", "source": {"type": "base64", "media_type": "image/png", "data": "<BASE64>"}},
        ],
    }
]

# Observed response text: "Red"