Codestral 25.08 (EU) vs MiniMax M3 Thinking
MiniMax M3 Thinking is cheaper on output tokens, while MiniMax M3 Thinking offers a larger context window. Choose Codestral 25.08 (EU) or MiniMax M3 Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Codestral 25.08 (EU) | MiniMax M3 Thinking |
|---|---|---|
| Provider | Eden AI | NanoGPT |
| Input / 1M tokens | $0.33 | $0.23 |
| Output / 1M tokens | $0.99 | $0.96 |
| Context window | 256K | 512K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Jul 2025 | Jun 2026 |
| LiveBench score | — | 70.0 |
FAQ
Is Codestral 25.08 (EU) or MiniMax M3 Thinking cheaper?
MiniMax M3 Thinking is cheaper on output tokens ($0.96 vs $0.99 per 1M).
Which has the larger context window, Codestral 25.08 (EU) or MiniMax M3 Thinking?
MiniMax M3 Thinking has the larger context window (512K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.