
Kimi K2 Instruct
Trillion-parameter open-weight MoE flagship for agentic tool use and coding.
About
Kimi K2 Instruct is Moonshot AI's flagship open-weight model, released on July 11, 2025. It is a mixture-of-experts model with 1 trillion total parameters and 32.6 billion activated per forward pass, trained on 15.5 trillion tokens with the Muon optimizer. Moonshot designed it specifically for tool use, reasoning, and autonomous problem solving.
The September 2025 Kimi-K2-Instruct-0905 update doubled context to 256K tokens and improved agentic coding, while the later K2 Thinking variant targets long tool-call sequences. Weights are distributed under a Modified MIT license with an attribution clause for very large commercial deployments, published on Hugging Face and compatible with vLLM, SGLang, and TensorRT-LLM.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 106; Trending score 90/100 from researcher assessment.