Kimi K2-Thinking-0905

Overview

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.

Kimi K2-Thinking-0905 was released on September 5, 2025.

Benchmarks

Kimi K2-Thinking-0905 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Sun Dec 07 2025

Pricing

Pricing, performance, and capabilities for Kimi K2-Thinking-0905 across different providers:

Example Outputs

API Access