Model specification · Moonshot AI

Kimi K2 Thinking

moonshotai/kimi-k2-thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

SpecificationsReported values
Context window
262K
Maximum output
100K
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
Moderated
No
Input modalities
text
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.600 / M
Output$2.50 / M
Benchmark indexesReported indexes
Intelligence
17.3
Coding
21
Agentic
1.8
Design Arena Elo
1136
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00850
Long analysis100K / 4K × 150%$0.048
Workday20K / 2K × 1,00030%$14.30
More from Moonshot AIAll Moonshot AI models
ModelContextInput / MOutput / MIntel.
Kimi K31.0M$3.00$15.0057.1
Kimi K2.6262K$0.600$3.4144.2
Kimi K2.7 Code262K$0.730$3.5041.9
Kimi K2.5262K$0.570$2.8535.4