Mistral Codestral 2508 vs Qwen3 Coder 480B A35B
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Both cost about the same at a typical 3:1 input/output mix.
- Both accept prompts up to 256K tokens.
- Codestral 2508's best provider was more reliable over 24 h: 100% vs 93.8%.
| Codestral 2508 | Qwen3 Coder 480B A35B | |
|---|---|---|
| Vendor | Mistral | Qwen |
| Released | 2025-08-01 | 2025-07-23 |
| Input / 1M | $0.30 | $0.30 |
| Output / 1M | $0.90 | $1.00 |
| Cached input / 1M | $0.03 | $0.10 |
| Blended / 1M (3:1) | $0.45 | $0.475 |
| Context | 256K | 262K |
| Max output | 205K | 66K |
| Accepts | text, file | text |
| Reasoning | No | No |
| Providers on OpenRouter | 2 | 2 |
| Cheapest provider, output | $0.90 | $1.00 |
| Best provider uptime, 24 h | 100% | 93.8% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Codestral 2508
$31.50 per month$1.05 per day
Qwen3 Coder 480B A35B
$33.00 per month$1.10 per day
Codestral 2508 saves $1.50 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Codestral 2508 with
Compare Qwen3 Coder 480B A35B with