modelgrep
M

MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905

77th smartest of 178ToolsJSON
Use via OpenRouter ↗
Intelligence
30.9
77th of 178
Design Elo
1152
Website
Speed
150
30th fastest
Latency
245ms
first token
Input price
$0.600
174th cheapest
Context
262K
262K max out

How it compares

Smarter than57%
of all ranked models
Faster than90%
of all ranked models
Cheaper than42%
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 · via OpenRouter
Artificial Analysis55th percentile
Intelligence Index
30.9
Coding Index
25.9
Agentic Index
37.7
GPQA Diamond
77%
Humanity's Last Exam
6%
SciCode
31%
Tau²-Bench (agentic)
73%
Design Arena · Elo672 tournaments
Website
1152
codecategories
1150

Providers & pricing (3)

ProviderIn $/MOut $/MUptime
Novitafp8$0.600$2.5099.3%
AtlasCloudfp8$0.600$2.5099.8%
Groqcache$1.00$3.00100%

Specifications

Context window262K
Max output262K
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 174th cheapest of 298 paid models.

How smart is Kimi K2 0905?

Kimi K2 0905 scores 30.9 on the Artificial Analysis Intelligence Index, ranking 77th of 178 benchmarked models, with a GPQA Diamond score of 77%.

How fast is Kimi K2 0905?

Kimi K2 0905 generates around 150 tokens per second with 245ms time-to-first-token (p50), the 30th fastest tracked model.

What is Kimi K2 0905's context window?

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

Compare head-to-head