MoonshotAI: Kimi K2 0905 (exacto)

MoonshotAI: Kimi K2 0905 (exacto)

moonshotai · Released Sep 4, 2025 Legacy
Intelligence #434 / 561
21.8 Our Score
Speed
— Not reported
Input #380 / 561
$0.600 per 1M tokens
Output #397 / 561
$2.50 per 1M tokens
Context #100 / 561
262,144 tokens

Analysis Summary

MoonshotAI: Kimi K2 0905 (exacto) sits in the Legacy tier on our leaderboard, ranked #434 of 561 published models on overall intelligence. At $0.600 input and $2.50 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and reasoning.

Editorial notes

Kimi K2 0905 (exacto) is a variant of the K2 family with a 262K context window and tool use, but no benchmark data is available to assess its capability independently.

Assessed May 14, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence0Technical0Value7Content2.5
Intelligence 0/10
Technical 0/10
Content 2.5/10
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.

Capabilities

Tool Use Function Calling

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.

99.8%
Avg Uptime
254ms
Best Latency (TTFT)
105 tok/s
Best Throughput
3/3
Active Endpoints
Available via: Novita, AtlasCloud, Groq