Model Library/Kimi K2 Instruct
Kimi

Kimi K2 Instruct

moonshotai/kimi-k2-instruct
by Moonshot AI
Input price
$0.57/ M tokens
Output price
$2.3/ M tokens
Context window
128Ktokens
Max output
96Ktokens

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.Specifically designed for tool use, reasoning, and autonomous problem-solving.

Funktionen

Serverless API

Dokumentation

moonshotai/kimi-k2-instruct is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

Verfügbare Serverless

Abfragen sofort ausführen, nur für die Nutzung bezahlen

Eingabe$0.57 / M Tokens
Ausgabe$2.3 / M Tokens
  1. API-Schlüssel erhalten

    Registrieren Sie sich und erstellen Sie einen Schlüssel, um den Code unten auszuführen. Die API ist OpenAI-kompatibel.

  2. Make your first request

    The API is OpenAI-compatible: point any OpenAI SDK at the base URL and pass this model ID.

    Base URL
    https://api.novita.ai/openaihttps://api.novita.ai/anthropic
    Model ID
    moonshotai/kimi-k2-instruct
    API Endpoint
    chat/completions
    1from openai import OpenAI
    2
    3client = OpenAI(
    4    api_key="<Your API Key>",
    5    base_url="https://api.novita.ai/openai"
    6)
    7
    8response = client.chat.completions.create(
    9    model="moonshotai/kimi-k2-instruct",
    10    messages=[
    11        {"role": "system", "content": "You are a helpful assistant."},
    12        {"role": "user", "content": "Hello, how are you?"}
    13    ],
    14    max_tokens=98304,
    15    temperature=0.7
    16)
    17
    18print(response.choices[0].message.content)