MoonshotAI: Kimi K2 0711
moonshotai/kimi-k2
126th smartest of 182Tools
Intelligence
19.4
126th of 182
Design Elo
1137
Website
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.570
180th cheapest
Context
131K
100K max out
How it compares
Smarter than31%
of all ranked models
Cheaper than46%
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 · Artificial Analysis & Design ArenaArtificial Analysis59th percentile
Intelligence Index
19.4
GPQA Diamond
77%
Humanity's Last Exam
7%
SciCode
35%
Tau²-Bench (agentic)
61%
Design Arena · Elo713 tournaments
Website
1137
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Novitafp8 | $0.570 | $2.30 | 131K | 100% |
Specifications
Context window131K
Max output100K
Knowledge cutoffDec 2024
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsmoonshotai/Kimi-K2-Instruct ↗
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 180th cheapest of 332 paid models.
How smart is Kimi K2 0711?
Kimi K2 0711 scores 19.4 on the Artificial Analysis Intelligence Index, ranking 126th of 182 benchmarked models, with a GPQA Diamond score of 77%.
What is Kimi K2 0711's context window?
Kimi K2 0711 supports a 131K-token context window and can output up to 100K tokens. It accepts text input.