Intelligence index
Outperforms 59% of compared models
Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.
It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
- Input / output price
- $0.6/$2.5per 1M tokens
- Context
- 262K
- Released
- 2025-11-06
Pricing
Artificial Analysis
Explore rankingsDesign Arena
Elo scores and win rates across design and agent tasks.
Model Arena
Website
1111Elo
Win rate 48.8%
Related Models
Kimi K3.1 Pro
moonshotaiKimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.
- Context
- 1.0M
- Max output
- 943.7K
- Released
- 2026-10-23
- Input
- $2/M
- Output
- $10/M
- Cache read
- $0.2/M
Kimi K3
moonshotaiKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
- Context
- 1.0M
- Max output
- 943.7K
- Released
- 2026-07-16
- Input
- $0.159/M
- Output
- $11.5/M
- Cache read
- $0.149/M
Kimi K2.6
moonshotaiKimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.
- Context
- 262K
- Max output
- 235.9K
- Released
- 2026-04-20
- Input
- $0.65/M
- Output
- $3.41/M
- Cache read
- $0.15/M