Key Takeaways
Kimi K2 0711 wins:
- No clear advantages in compared metrics
Kimi K2 Thinking wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
- Has reasoning mode
Price Advantage
Kimi K2 Thinking
Benchmark Advantage
Kimi K2 Thinking
Context Window
Kimi K2 Thinking
Speed
Kimi K2 Thinking
Pricing Comparison
Price Comparison
| Metric | Kimi K2 0711 | Kimi K2 Thinking | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.50 | $0.40 | Kimi K2 Thinking |
| Output (per 1M tokens) | $2.40 | $1.75 | Kimi K2 Thinking |
| Cache Read (per 1M) | N/A | $200000.00 | Kimi K2 Thinking |
Using a 3:1 input/output ratio, Kimi K2 Thinking is 24% cheaper overall.
Kimi K2 0711 Providers
Nebius $0.50 (Cheapest)
Vercel $0.55
DeepInfra $0.55
Novita $0.57
Moonshot AI $0.60
Kimi K2 Thinking Providers
Chutes $0.40 (Cheapest)
DeepInfra $0.47
Parasail $0.50
SiliconFlow $0.55
AtlasCloud $0.60
Benchmark Comparison
8
Benchmarks Compared
0
Kimi K2 0711 Wins
6
Kimi K2 Thinking Wins
Benchmark Scores
| Benchmark | Kimi K2 0711 | Kimi K2 Thinking | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 26.2 | 40.7 | |
Coding Index Code generation & understanding | 22.1 | 34.8 | |
Math Index Mathematical reasoning | 57.0 | 94.7 | |
MMLU Pro Academic knowledge | 82.4 | 84.8 | |
GPQA Graduate-level science | 76.6 | 83.8 | |
LiveCodeBench Competitive programming | 55.6 | 85.3 | |
Aider Real-world code editing | 59.1 | - | - |
AIME Competition math | 69.3 | - | - |
Kimi K2 Thinking significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Kimi K2 0711
Other models
Context & Performance
Context Window
Kimi K2 0711
131,072
tokens
Kimi K2 Thinking
262,144
tokens
Max output: 65,535 tokens
Kimi K2 Thinking has a 50% larger context window.
Speed Performance
| Metric | Kimi K2 0711 | Kimi K2 Thinking | Winner |
|---|---|---|---|
| Tokens/second | 44.5 tok/s | 82.1 tok/s | |
| Time to First Token | 0.62s | 0.64s |
Kimi K2 Thinking responds 85% faster on average.
Capabilities
Feature Comparison
| Feature | Kimi K2 0711 | Kimi K2 Thinking |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Kimi K2 0711 | Kimi K2 Thinking |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | Moonshotai | Moonshotai |
| Released | Jul 2025 | Nov 2025 |
Kimi K2 0711 Modalities
Input
text
Output
text
Kimi K2 Thinking Modalities
Input
text
Output
text