modelgrep
moonshotai logo

MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905

113th smartest of 182ToolsJSON
Use via OpenRouter ↗
Intelligence
23.5
113th of 182
Design Elo
Speed
tokens/sec
Latency
first token
Input price
$0.600
185th cheapest
Context
262K
100K max out

How it compares

Smarter than38%
of all ranked models
Cheaper than44%
of all ranked models

Overview

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Benchmarks

independent · Artificial Analysis & Design Arena
Artificial Analysis66th percentile
Intelligence Index
23.5
GPQA Diamond
77%
Humanity's Last Exam
6%
SciCode
31%
Tau²-Bench (agentic)
73%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Novitafp8$0.600$2.5099.6%
Groqcache$1.00$3.00100%

Specifications

Context window262K
Max output100K
Knowledge cutoffDec 2024
Input modalitiestext
Output modalitiestext
Prompt cachingSupported
Cache read price
ModeratedNo

Kimi K2 0905 FAQ

How much does Kimi K2 0905 cost?

Kimi K2 0905 costs $0.600 per million input tokens and $2.50 per million output tokens via OpenRouter, making it 185th cheapest of 332 paid models.

How smart is Kimi K2 0905?

Kimi K2 0905 scores 23.5 on the Artificial Analysis Intelligence Index, ranking 113th of 182 benchmarked models, with a GPQA Diamond score of 77%.

What is Kimi K2 0905's context window?

Kimi K2 0905 supports a 262K-token context window and can output up to 100K tokens. It accepts text input.

Compare head-to-head