Compare
Codestral 2508 (batch) vs …
Put models side by side on context, price, speed and availability.
| Model | |
|---|---|
| Overview | |
| Developer | Mistral |
| Context tokens | 250K |
| Max output tokens | 200K |
| Input | |
| Output | |
| Providers | 2 |
| Released | Aug 1, 2025 |
| Pricing | |
| Input per 1M | $0.15 |
| Output per 1M | $0.45 |
| Cache read per 1M | $0.01 |
| Performance | |
| Latency p50, median provider | 0.50s |
| Throughput p50, median provider | 113 tps |
| Uptime last 24h | 100.00% |
