Key Takeaways
Codestral 2508 wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
Kimi K2 Thinking wins:
- Has reasoning mode
Price Advantage
Codestral 2508
Benchmark Advantage
Codestral 2508
Context Window
Codestral 2508
Speed
N/A
Pricing Comparison
Price Comparison
| Metric | Codestral 2508 | Kimi K2 Thinking | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.30 | $0.47 | Codestral 2508 |
| Output (per 1M tokens) | $0.90 | $2.00 | Codestral 2508 |
| Cache Read (per 1M) | N/A | $0.14 | Kimi K2 Thinking |
Using a 3:1 input/output ratio, Codestral 2508 is 47% cheaper overall.
Codestral 2508 Providers
No provider data available
Kimi K2 Thinking Providers
No provider data available
Benchmark Comparison
1
Benchmarks Compared
0
Codestral 2508 Wins
0
Kimi K2 Thinking Wins
Benchmark Scores
| Benchmark | Codestral 2508 | Kimi K2 Thinking | Winner |
|---|---|---|---|
Aider Real-world code editing | 11.1 | - | - |
Both models show comparable benchmark performance.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Other models
Context & Performance
Context Window
Codestral 2508
256,000
tokens
Kimi K2 Thinking
131,072
tokens
Codestral 2508 has a 49% larger context window.
Speed Performance
Speed benchmarks not available for these models
Capabilities
Feature Comparison
| Feature | Codestral 2508 | Kimi K2 Thinking |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Codestral 2508 | Kimi K2 Thinking |
|---|---|---|
| License | Open Source | Open Source |
| Author | Mistral AI | Moonshotai |
| Released | Aug 2025 | Nov 2025 |
Codestral 2508 Modalities
Input
text
Output
text
Kimi K2 Thinking Modalities
Input
text
Output
text