Kimi K2 0905

moonshotai/kimi-k2-0905

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.

Recursos

API serverless

Documentação

moonshotai/kimi-k2-0905 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.

Serverless disponível

Execute consultas imediatamente, pague apenas pelo uso

Entrada$0.6 / M Tokens

Saída$2.5 / M Tokens

Use os exemplos de código a seguir para integrar com nossa API:

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-k2-0905",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=262144,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

Informações

Provedor

MoonshotAI

Quantização

fp8

Funcionalidades compatíveis

Comprimento do contexto

262144

Saída máxima

262144

Serverless

Compatível

Function Calling

Compatível

Structured Output

Compatível

API da Anthropic

Compatível

Capacidades de entrada

text

Capacidades de saída

text

Tudo o que você precisa para criar IA de produção.

Mais de 200 modelos, GPUs sob demanda e ambientes de execução de agentes seguros — unificados em uma única API. Grátis para começar, escala conforme você cresce.