Kimi K2 0711

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.

ChatMoonshot131k tokens$0.6213 / $2.5071 · 1M

moonshotai/kimi-k2

Contexto
131k tokens
Máx. completion
100,352
Tools
Sí
JSON
No
Lanzamiento
2025-07-11

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es Kimi K2 0711?
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. Kimi K2 0711 corre en el API de Geek Hub (compatible con OpenAI). Id: moonshotai/kimi-k2.
¿Kimi K2 0711 es gratis?
No. El input cuesta $0.6213 / 1M tokens y el output $2.5071 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de Kimi K2 0711?
Kimi K2 0711 tiene una ventana de 131k tokens. Soporta hasta 100,352 tokens de completion.
¿Kimi K2 0711 soporta tool calling y structured outputs?
Kimi K2 0711 acepta tools y tool_choice para function calling. No lista structured outputs en este endpoint.
¿Cuándo se lanzó Kimi K2 0711?
Kimi K2 0711 se lanzó el 11 de julio de 2025.

Más modelos de Moonshot