MiniMax-M2.5 vs Hy3

Specs, VRAM requirements and download trends — updated 23 October 2026.

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

Specification comparison

Differences are highlighted; identical values are muted.

Specification MiniMax-M2.5 Hy3
Deployment Open weights · also via API Open weights · also via API
Parameters 228.7 B 298.8 B
Architecture MiniMaxM2ForCausalLM HYV3ForCausalLM
Context length 196,608 262,144
Licence other apache-2.0
Commercial use Unknown Allowed
Languages — —
Downloads 30d 859,423 797,888
Downloads all time 5.8 M 842 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-02-12 2026-07-02
API input price / 1M tokens $0.27 $0.13
API output price / 1M tokens $0.95 $0.53
Est. cost per 1M input + 1M output tokens $1.22 $0.66
Cached input / 1M tokens $0.03 $0.033
AA Intelligence Index 22.8 —
AA Coding Index — —
AA Agentic Index — —
Max output tokens 32,768 128,000
API providers 7 5
Tool calling Yes Yes
Reasoning mode Yes Yes

API cost

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

MiniMax-M2.5 $1.22
Hy3 $0.66

Hy3 is 1.8× cheaper at list price.

Download trend

Daily snapshots, last 88 days (28 Jul – 23 Oct)

859 K188 K
MiniMax-M2.5 Hy3

VRAM side by side

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

MiniMax-M2.5 · fp16 @ 192K ctx 1,077.0 GB / 24 GB
❌ Won’t fit
Hy3 · fp16 @ 256K ctx 2,092.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons