MoonshotAI: Kimi K2 0905 (exacto)

MoonshotAI: Kimi K2 0905 (exacto)

moonshotai · Released Sep 4, 2025 Legacy
Awaiting
Review
Benchmarks pending

Performance Profile

Intelligence0Technical0Value7Content3
Intelligence 0/10
Technical 0/10
Content 3/10
Value 7/10

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.

$0.60 / 1M
Input Price
$2.50 / 1M
Output Price
262,144 tokens
Context Window

Capabilities

Tool Use Function Calling

Architecture

ModalityText → Text
TokenizerOther

How does MoonshotAI: Kimi K2 0905 (exacto) stack up?

Compare side-by-side with other legacy models.

Compare Models

Model Information

OpenRouter ID moonshotai/kimi-k2-0905:exacto
Providermoonshotai
Release Date September 4, 2025
Context Length262,144 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.60 $0.000600
Output $2.50 $0.002500

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

99%
Avg Uptime
132ms
Best Latency (TTFT)
170 tok/s
Best Throughput
4/4
Active Endpoints
Available via: SiliconFlow, Novita, Fireworks, Groq