Mistral: Codestral 2508 vs Mistral Large 3
Side-by-side comparison. Updated 2026-06-08.
Verdict
Mistral: Codestral 2508 wins on higher overall score (8.4 vs 8.3, +0.1).
- ~85% cheaper input
At a Glance
| Attribute | Mistral: Codestral 2508 | Mistral Large 3 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Tags | Coding | general |
| Context | 256,000 tokens | 128,000 tokens |
| Input price | $0.30/1M | $2.00/1M |
| Output price | $6.00/1M | $6.00/1M |
| Input modalities | Text, File | Text |
| Output modalities | Text | Text |
Mistral: Codestral 2508 Strengths
- Specialized for coding with fill-in-the-middle (FIM) support
- Low-latency design for high-frequency coding tasks
- Strong at code correction and test generation
- 256K context window for large codebase understanding
- Mistral-grade quality at competitive pricing ($0.30/$0.90)
Mistral Large 3 Strengths
- Excellent multilingual
- Strong coding
- Good reasoning
- European data sovereignty focus