token.app › Compare › MiniMax M3 vs DeepSeek V4 Flash 0731
MiniMax M3 vs DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads on 2 of 2 shared benchmarks. MiniMax M3 is 1.3× cheaper per token on a blended 3:1 basis.
Head to head
Blended price uses a 3:1 input:output mix
| MiniMax M3 | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | MiniMax | DeepSeek |
| Input $/1M | $0.300 | $0.440 |
| Output $/1M | $1.20 | $1.32 |
| Blended $/1M | $0.525 | $0.660 |
| Context window | 1.0M | 1.0M |
| Max output | 512K | 131K |
| Released | May 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 90.9% | 91.0% |
| OTIS Mock AIME | 71.1% | 94.4% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose MiniMax M3 if…
- Costs less per token — $0.525 vs $0.660 blended
Choose DeepSeek V4 Flash 0731 if…
- Higher GPQA Diamond (91.0% vs 90.9%)
- Higher OTIS Mock AIME (94.4% vs 71.1%)
- Newer model (released Jul 2026)
FAQ
Which is better, MiniMax M3 or DeepSeek V4 Flash 0731?
Across the 2 benchmarks both models have independently-run scores for, MiniMax M3 leads on 0 and DeepSeek V4 Flash 0731 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is MiniMax M3 cheaper than DeepSeek V4 Flash 0731?
MiniMax M3 is cheaper: $0.525 versus $0.660 per million tokens blended at 3:1 input:output. Input alone: $0.300 vs $0.440. Output alone: $1.20 vs $1.32.
What context windows do MiniMax M3 and DeepSeek V4 Flash 0731 have?
MiniMax M3: 1,048,576 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes MiniMax M3 and DeepSeek V4 Flash 0731?
MiniMax M3 is made by MiniMax. DeepSeek V4 Flash 0731 is made by DeepSeek.