Kimi K2 Instruct 0905 · deepinfra

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.

Modelo baseTodos los modelos de esta baseTodos los modelos del proveedoral proveedor

Lea también: Precios de la API de Kimi: Kimi K3.1 Pro, K3, K2.6 y K2.7 Code en cada proveedor

Todos los modelos de Moonshot Kimi en todos los proveedores

Entrada, $/1M $0.40

Salida, $/1M $2.00

Contexto 131 072

Acepta —

Última comprobación 04.11.2026 12:00:14 UTC

Fuente —