modelgrep
M

MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6

33rd smartest of 179ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
42.9
33rd of 179
Design Elo
1362
3D
Speed
124
41st fastest
Latency
509ms
first token
Input price
$0.680
182nd cheapest
Context
262K
262K max out

How it compares

Smarter than82%
of all ranked models
Faster than87%
of all ranked models
Cheaper than39%
of all ranked models

Overview

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Benchmarks

independent · via OpenRouter
Artificial Analysis79th percentile
Intelligence Index
42.9
Coding Index
38.4
Agentic Index
58.7
GPQA Diamond
79%
Humanity's Last Exam
18%
SciCode
40%
Tau²-Bench (agentic)
94%
Design Arena · Elo24,901 tournaments
3D
1362
codecategories
1331
UI Component
1327
Game Dev
1325
Website
1321
Data Viz
1303
webapps
1272
agenticslides(html)
1252
agentichtmlslides
1248
fullstack
1236
svg
1235
mobileapps
1234
godotgamedev
1218
agenticslides(python-pptx)
1187
agenticslides
1187
agenticgamedev
1184
androidnative
1184

Providers & pricing (20)

ProviderIn $/MOut $/MUptime
Io Netint4$0.680$3.4196.1%
Decartfp4$0.680$3.4196.3%
Baidufp4$0.684$3.42100%
Inceptronint4$0.730$3.5099.6%
Chutesint4$0.740$3.5099.2%
Cloudflare$0.740$3.5075.2%
Parasailint4$0.750$3.5099%
DeepInfrafp4$0.750$3.5095.7%
SiliconFlowfp8$0.770$4.0099.7%
Novita$0.800$3.4099.9%
DigitalOcean$0.807$3.4063.9%
Veniceint4$0.850$4.6682.2%
StreamLake$0.855$3.6099.6%
Moonshot AIint4$0.950$4.00100%
WandBfp4$0.950$4.0099.9%
AtlasCloudint4$0.950$4.0099.9%
Phala$1.09$4.6098.6%
Together$1.20$4.50100%
Fireworks$0.950$4.00
BaseTenfp4$0.950$4.00

Specifications

Context window262K
Max output262K
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price$0.340/M
ModeratedNo

Kimi K2.6 FAQ

How much does Kimi K2.6 cost?

Kimi K2.6 costs $0.680 per million input tokens and $3.41 per million output tokens via OpenRouter, making it 182nd cheapest of 298 paid models.

How smart is Kimi K2.6?

Kimi K2.6 scores 42.9 on the Artificial Analysis Intelligence Index, ranking 33rd of 179 benchmarked models, with a GPQA Diamond score of 79%.

How fast is Kimi K2.6?

Kimi K2.6 generates around 124 tokens per second with 509ms time-to-first-token (p50), the 41st fastest tracked model.

What is Kimi K2.6's context window?

Kimi K2.6 supports a 262K-token context window and can output up to 262K tokens. It accepts text, image input.

Compare head-to-head