Key Takeaways
Codestral 2508 wins:
- Larger context window
Mistral Nemo wins:
- Cheaper input tokens
- Cheaper output tokens
- Higher intelligence benchmark
Price Advantage
Mistral Nemo
Benchmark Advantage
Mistral Nemo
Context Window
Codestral 2508
Speed
N/A
Pricing Comparison
Price Comparison
| Metric | Codestral 2508 | Mistral Nemo | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.30 | $0.02 | Mistral Nemo |
| Output (per 1M tokens) | $0.90 | $0.04 | Mistral Nemo |
Using a 3:1 input/output ratio, Mistral Nemo is 94% cheaper overall.
Codestral 2508 Providers
Mistral $0.30 (Cheapest)
Mistral Nemo Providers
Chutes $0.02 (Cheapest)
DeepInfra $0.02 (Cheapest)
Novita $0.04
Mistral $0.15
Azure $0.30
Benchmark Comparison
5
Benchmarks Compared
0
Codestral 2508 Wins
0
Mistral Nemo Wins
Benchmark Scores
| Benchmark | Codestral 2508 | Mistral Nemo | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | - | 25.0 | - |
MMLU Pro Academic knowledge | - | 26.4 | - |
GPQA Graduate-level science | - | 8.7 | - |
Aider Real-world code editing | 11.1 | - | - |
BBH Big-Bench Hard | - | 36.1 | - |
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
Mistral Nemo
131,072
tokens
Max output: 16,384 tokens
Codestral 2508 has a 49% larger context window.
Speed Performance
Speed benchmarks not available for these models
Capabilities
Feature Comparison
| Feature | Codestral 2508 | Mistral Nemo |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Codestral 2508 | Mistral Nemo |
|---|---|---|
| License | Open Source | Open Source |
| Author | Mistral AI | Mistral AI |
| Released | Aug 2025 | Jul 2024 |
Codestral 2508 Modalities
Input
text
Output
text
Mistral Nemo Modalities
Input
text
Output
text