Skip to main content

​
Setup

export MOONSHOT_API_KEY="sk-..."

​
Basic Usage

from definable.model import MoonshotChat
from definable.model.message import Message

model = MoonshotChat(id="kimi-k2-turbo-preview")
response = model.invoke(
    messages=[Message(role="user", content="Hello!")],
    assistant_message=Message(role="assistant", content=""),
)
print(response.content)

​
Parameters

​
id
str
default:"kimi-k2-turbo-preview"
Model identifier.
​
api_key
str
Moonshot API key. Defaults to the MOONSHOT_API_KEY environment variable.
​
base_url
str
default:"https://api.moonshot.ai/v1"
Moonshot API base URL.
​
temperature
float
Sampling temperature.
​
max_tokens
int
Maximum output tokens.

​
Streaming

from definable.model.message import Message

for chunk in model.invoke_stream(
    messages=[Message(role="user", content="Write a haiku about coding.")],
    assistant_message=Message(role="assistant", content=""),
):
    if chunk.content:
        print(chunk.content, end="", flush=True)

​
Async Usage

from definable.model.message import Message

response = await model.ainvoke(
    messages=[Message(role="user", content="Hello!")],
    assistant_message=Message(role="assistant", content=""),
)
Moonshot uses an OpenAI-compatible API. All standard parameters like temperature, max_tokens, top_p, and stop are supported.