modelgrep
M

MoonshotAI: Kimi K2 0711

moonshotai/kimi-k2

149th smartest of 178Tools
Use via OpenRouter ↗
Intelligence
14.4
149th of 178
Design Elo
1095
Website
Speed
15
272nd fastest
Latency
1.5s
first token
Input price
$0.570
169th cheapest
Context
131K
33K max out

How it compares

Smarter than16%
of all ranked models
Faster than8%
of all ranked models
Cheaper than43%
of all ranked models

Overview

Kimi K2 Instruct 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 is optimized for...

Benchmarks

independent · via OpenRouter
Artificial Analysis18th percentile
Intelligence Index
14.4
Coding Index
10.5
Agentic Index
6.9
GPQA Diamond
54%
Humanity's Last Exam
4%
SciCode
22%
Tau²-Bench (agentic)
21%
Design Arena · Elo596 tournaments
Website
1095
UI Component
1088
codecategories
1085
Data Viz
1062
Game Dev
1043

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Novitafp8$0.570$2.30100%

Specifications

Context window131K
Max output33K
Knowledge cutoffDec 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Kimi K2 0711 FAQ

How much does Kimi K2 0711 cost?

Kimi K2 0711 costs $0.570 per million input tokens and $2.30 per million output tokens via OpenRouter, making it 169th cheapest of 298 paid models.

How smart is Kimi K2 0711?

Kimi K2 0711 scores 14.4 on the Artificial Analysis Intelligence Index, ranking 149th of 178 benchmarked models, with a GPQA Diamond score of 54%.

How fast is Kimi K2 0711?

Kimi K2 0711 generates around 15 tokens per second with 1.5s time-to-first-token (p50), the 272nd fastest tracked model.

What is Kimi K2 0711's context window?

Kimi K2 0711 supports a 131K-token context window and can output up to 33K tokens. It accepts text input.

Compare head-to-head