MiniMax-M2.7 vs DeepSeek-V3-0324
Specs, VRAM requirements and download trends — updated 17 October 2026.
deepseek-ai · B · Open weights
Params
684.5 B
Context
163,840
30d
150 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | MiniMax-M2.7 | DeepSeek-V3-0324 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 228.7 B | 684.5 B |
| Architecture | MiniMaxM2ForCausalLM | DeepseekV3ForCausalLM |
| Context length | 204,800 | 163,840 |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 302,065 | 149,937 |
| Downloads all time | 8.1 M | 10.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-09 | 2025-03-24 |
| API input price / 1M tokens | $0.21 | $0.29 |
| API output price / 1M tokens | $0.84 | $1.14 |
| Est. cost per 1M input + 1M output tokens | $1.05 | $1.43 |
| Cached input / 1M tokens | $0.042 | $0.11 |
| AA Intelligence Index | — | — |
| AA Coding Index | 52.6 | 21.2 |
| AA Agentic Index | 15.3 | 0.8 |
| Max output tokens | 176,947 | 115,200 |
| API providers | 2 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
MiniMax-M2.7
$1.05
DeepSeek-V3-0324
$1.43
MiniMax-M2.7 is 1.4× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.5 M150 K
MiniMax-M2.7
DeepSeek-V3-0324
A overtook B on 30 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
MiniMax-M2.7 · fp16 @ 200K ctx
1,111.2 GB / 24 GB
DeepSeek-V3-0324 · fp16 @ 160K ctx
2,811.5 GB / 24 GB