Kimi K2-Thinking-0905

Overview

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. API access is available through DeepInfra, Novita, Fireworks.

Benchmarks

Benchmarks

Kimi K2-Thinking-0905 Performance Across Datasets

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

Share

llm-stats.com - Sat Feb 21 2026

Pricing

Pricing

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

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
DeepInfrafp4	$0.47	$2.00	262.1K	262.1K	—	—	fp4	Text Image Audio Video	Text Image Audio Video
Novitabf16	$0.48	$2.00	262.1K	262.1K	—	—	bf16	Text Image Audio Video	Text Image Audio Video
Fireworks	$0.60	$2.50	262.1K	262.1K	—	—	—	Text Image Audio Video	Text Image Audio Video

Price Comparison for Kimi K2-Thinking-0905

Price per 1M input tokens (USD), lower is better

Share

llm-stats.com - Sat Feb 21 2026

API Access