token.app › Compare › Llama 4 Maverick vs DeepSeek V4 Flash 0731
Llama 4 Maverick vs DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads on 2 of 2 shared benchmarks. DeepSeek V4 Flash 0731 is 3.1× cheaper per token on a blended 3:1 basis.
Head to head
Blended price uses a 3:1 input:output mix
| Llama 4 Maverick | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Input $/1M | $0.200 | $0.090 |
| Output $/1M | $0.800 | $0.180 |
| Blended $/1M | $0.350 | $0.113 |
| Context window | 1.0M | 1.0M |
| Max output | 16K | 384K |
| Released | Apr 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 67.0% | 91.0% |
| OTIS Mock AIME | 20.6% | 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 Llama 4 Maverick if…
- No clear advantage on the data we hold.
Choose DeepSeek V4 Flash 0731 if…
- Costs less per token — $0.113 vs $0.350 blended
- Higher GPQA Diamond (91.0% vs 67.0%)
- Higher OTIS Mock AIME (94.4% vs 20.6%)
- Newer model (released Jul 2026)
FAQ
Which is better, Llama 4 Maverick or DeepSeek V4 Flash 0731?
Across the 2 benchmarks both models have independently-run scores for, Llama 4 Maverick 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 Llama 4 Maverick cheaper than DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.113 versus $0.350 per million tokens blended at 3:1 input:output. Input alone: $0.200 vs $0.090. Output alone: $0.800 vs $0.180.
What context windows do Llama 4 Maverick and DeepSeek V4 Flash 0731 have?
Llama 4 Maverick: 1,048,576 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes Llama 4 Maverick and DeepSeek V4 Flash 0731?
Llama 4 Maverick is made by Meta. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons