Llama 4 Maverick 17B 128E Instruct vs MiniMax M3
Llama 4 Maverick 17B 128E Instruct is cheaper on output tokens, while MiniMax M3 offers a larger context window. Choose Llama 4 Maverick 17B 128E Instruct or MiniMax M3 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Llama 4 Maverick 17B 128E Instruct | MiniMax M3 |
|---|---|---|
| Provider | Vertex | MiniMax |
| Input / 1M tokens | $0.35 | $0.30 |
| Output / 1M tokens | $1.15 | $1.20 |
| Context window | 524K | 1M |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Apr 2025 | Jun 2026 |
| LMArena (Chatbot Arena) Elo score | 1287 | 1433 |
| LMArena Vision Elo score | 1142 | 1253 |
| GPQA Diamond score | — | 90.9 |
| Epoch Capabilities Index score | — | 147 |
| LMArena WebDev Elo score | — | 1482 |
| LiveBench score | — | 67.3 |
FAQ
Is Llama 4 Maverick 17B 128E Instruct or MiniMax M3 cheaper?
Llama 4 Maverick 17B 128E Instruct is cheaper on output tokens ($1.15 vs $1.20 per 1M).
Which has the larger context window, Llama 4 Maverick 17B 128E Instruct or MiniMax M3?
MiniMax M3 has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.