Kimi K2-Thinking-0905 (Reasoning)

by Moonshot AI

Kimi K2-Thinking-0905 (Reasoning) is a reasoning model from Moonshot AI, released on September 5, 2025. It has a 262K-token context window and can generate up to 262K output tokens. API pricing is $0.47 per 1M input tokens and $2 per 1M output tokens. It ranks #62 of 220 models by Intelligence Score with a score of 35.7.

Kimi K2 Thinking is the latest, most capable version of open-source thinking model. Starting with Kimi K2, it is built as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks by dramatically scaling multi-step reasoning depth and maintaining stable tool-use across 200–300 sequential calls. At the same time, K2 Thinking is a native INT4 quantization model with 256k context window, achieving lossless reductions in inference latency and GPU memory usage. Key features include deep thinking & tool orchestration with end-to-end training to interleave chain-of-thought reasoning with function calls, native INT4 quantization via Quantization-Aware Training (QAT) achieving lossless 2x speed-up, and stable long-horizon agency maintaining coherent goal-directed behavior across up to 200–300 consecutive tool invocations.

Key specs

Compare on the AI leaderboard · All AI models

More models from Moonshot AI

• Kimi K3 (Reasoning) — Moonshot AI
• Kimi K2.7 Code (Reasoning) — Moonshot AI
• Kimi K2 Instruct — Moonshot AI
• Kimi K2-Instruct-0905 — Moonshot AI
• Kimi-k1.5 — Moonshot AI
• Kimi K2 Base — Moonshot AI