Compare

Kimi K2 Thinking vs …

Put models side by side on context, price, speed and availability.

All models
Side-by-side comparison of the selected models
Model
Kimi K2 ThinkingMoonshotAI
Overview
Developer MoonshotAI
Context tokens256K
Max output tokens96K
Input text
Output text
Providers 2
Released Nov 6, 2025
Pricing
Input per 1M$0.60
Output per 1M$2.50
Cache read per 1M$0.15
Performance
Latency p50, median provider0.93s
Throughput p50, median provider95 tps
Uptime last 24h100.00%

Add a model