Hy3 vs MiniMax-M2.1

Specs, VRAM requirements and download trends — updated 24 October 2026.

tencent · A · Open weights
Params
298.8 B
Context
262,144
30d
837 K
apache-2.0 · commercial OK
MiniMaxAI · B · Open weights
Params
228.7 B
Context
196,608
30d
12 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Hy3 MiniMax-M2.1
Deployment Open weights · also via API Open weights · also via API
Parameters 298.8 B 228.7 B
Architecture HYV3ForCausalLM MiniMaxM2ForCausalLM
Context length 262,144 196,608
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages — —
Downloads 30d 837,193 11,542
Downloads all time 882 K 505 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-07-02 2025-12-20
API input price / 1M tokens $0.13 $0.30
API output price / 1M tokens $0.53 $1.20
Est. cost per 1M input + 1M output tokens $0.66 $1.50
Cached input / 1M tokens $0.033 $0.03
AA Intelligence Index — 20.9
AA Coding Index — —
AA Agentic Index — —
Max output tokens 128,000 131,072
API providers 5 1
Tool calling Yes Yes
Reasoning mode Yes Yes

API cost

Estimated cost of 1M input + 1M output tokens via OpenRouter

Hy3 $0.66
MiniMax-M2.1 $1.50

Hy3 is 2.3× cheaper at list price.

Download trend

Daily snapshots, last 26 days (29 Sep – 24 Oct)

837 K11 K
Hy3 MiniMax-M2.1

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

MiniMax-M2.1 · fp16 @ 192K ctx 1,076.9 GB / 24 GB
❌ Won’t fit
Hy3 · fp16 @ 256K ctx 2,092.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons