Kimi K2 Instruct · deepinfra

Kimi K2 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.

BasismodellAlle Modelle dieser BasisAlle Modelle des Anbieterszum Anbieter

Lesen Sie auch: Kimi-API-Preise: Kimi K3.1 Pro, K3, K2.6 und K2.7 Code bei jedem Anbieter

Alle Moonshot Kimi-Modelle bei allen Anbietern

Eingabe, $/1M $0.50

Ausgabe, $/1M $2.00

Kontext 131 072

Akzeptiert —

Zuletzt geprüft 04.11.2026 12:00:14 UTC

Quelle —