moonshotai/kimi-k2
Data di rilascio: 2025-07-12
131,072 context · $0.57/M input tokens · $2.30/M output tokens
Kimi K2 Instruct 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 is optimized for...
Prezzi
Pay-per-use
Nessun costo iniziale, paga solo per ciò che usi
Prova il modello
Utilizzo API
Usa i seguenti esempi di codice per integrare la nostra API:
import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'moonshotai/kimi-k2',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'moonshotai/kimi-k2',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}Introduzione al modello
Moonshotai kimi-k2
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 bill
Kimi K2 Instruct 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 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
Why It Looks Great
- Large Language Model architecture for efficient processing
- 131072 context window for long document handling
- Competitive pricing at $0.5/$2.6 per million tokens
Key Features
- Context Window: 131072 tokens
- Max Output: N/A tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Moonshotai |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 131072 tokens |
| Max Output | tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.5 |
| Output | $2.6 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: moonshotai/kimi-k2
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "moonshotai/kimi-k2",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: moonshotai/kimi-k2
- Provider: Moonshotai
Info
Funzionalità supportate
Guida all'accesso API
Kimi K2 API
moonshotai/kimi-k2
Kimi K2 Instruct 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 is optimized for...
Input
$0.57 /M
Output
$2.3 /M
Contesto
131K
Output max
131K
Uso strumenti
Supportato
Prova Kimi K2 su WaveSpeedAI
Accedi a Kimi K2 tramite la nostra API unificata — compatibile con OpenAI, senza cold start, prezzi trasparenti.
Domande frequenti su Kimi K2
Quanto costa Kimi K2 via API?+
Prezzi su WaveSpeedAI: $0.57 per milione di token in input e $2.30 per milione di token in output. Prompt caching e batch processing sono fatturati separatamente e riducono il costo effettivo su carichi lunghi e ripetitivi.
Qual è la context window di Kimi K2?+
Kimi K2 supporta fino a 131K token di contesto e fino a 131K token di output per richiesta.
Kimi K2 è compatibile con OpenAI?+
WaveSpeedAI espone Kimi K2 su https://llm.wavespeed.ai/v1 tramite l’interfaccia Chat Completions compatibile con OpenAI. Per la maggior parte dei client OpenAI SDK basta cambiare base URL e API key; i campi opzionali dipendono dal modello.
Come si inizia con Kimi K2?+
Accedi a WaveSpeedAI, crea una API key in Access Keys e invia una richiesta a https://llm.wavespeed.ai/v1/chat/completions con il model id mostrato sopra. Consulta il catalogo attuale per disponibilità, funzionalità e prezzi.