Modeldex
Drag to turnCard front showing

MiniMaxVideoPromo

MiniMax-H3

Video generation model from MiniMax, 33B parameters.

MiniMaxAI/MiniMax-H3
Type
Video
Quality
85 · Top 15% on the LMArena Text to Video
Parameters
33B (33,122,992,896)
Downloads
4.8M in the last 30 days
Likes
6.2K
Access to weights
Open download
On Hugging Face since
Jul 28, 2026
Takes in
Text, Image
Puts out
Video
Access
Open weights
License
MiniMax H3 Community License Agreement
Rarity
Promo
Set number
959/1044
Open on Hugging FaceQuality 85Where to run it 1Meet its creatureBattle LTX-2.5

License read from the model’s Hugging Face card. Stats from MiniMax’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for MiniMax-H3, refreshed daily from Epoch AI and LMArena.

Top 15% of the 48 models on the LMArena Text to Video: #8.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Scores from LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

1 provider sells MiniMax-H3 through an API. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
Vercel AI Gatewayminimax/minimax-h3———

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

More from MiniMax

MiniMax

MiniMax-M3.1-Flash

CTX1M
New
Reasoning · Vision · Tools
TextImageVideoInput$0.15/M
TextOutput$0.60/M

Frontier multimodal coding model with 1M context window and tunable thinking depth

Open weightsMIT1044/1044
MiniMax

MiniMax-Music3

SIZE2.4B
Text to speech
TextDownloads6.2K/mo
AudioLikes1.5K

Text-to-audio model from MiniMax, 2.4B parameters.

Open weightsMIT971/1044
MiniMax

MiniMax-M3

CTX1M
75Quality
Reasoning · Vision · Tools
TextImageVideoInput$0.30/M
TextOutput$1.20/M

MiniMax multimodal model for long-context coding, perception, and agent planning

Open weightsMiniMax Community license913/1044
MiniMax

MiniMax-M2.7-highspeed

CTX205K
Reasoning · Tools
TextInput$0.60/M
TextOutput$2.40/M

Low-latency M2.7 variant for interactive coding plans and agent loops

Open weightsMIT837/1044
MiniMax

MiniMax-M2.7

CTX205K
70Quality
Reasoning · Tools
TextInput$0.30/M
TextOutput$1.20/M

Open MiniMax flagship for coding agents, office automation, and complex environments

Open weightsCustom license836/1044
MiniMax

MiniMax-M2.5-highspeed

CTX205K
Reasoning · Tools
TextInput$0.60/M
TextOutput$2.40/M

High-speed MiniMax model for low-latency coding and agent workflows

Open weightsMIT779/1044
MiniMax

MiniMax-M2.5

CTX205K
74Quality
Reasoning · Tools
TextInput$0.30/M
TextOutput$1.20/M

Prior MiniMax coding model for agent workflows, office edits, and automation

Open weightsModified MIT778/1044
MiniMax

MiniMax-M2.1

CTX205K
60Quality
Reasoning · Tools
TextInput$0.30/M
TextOutput$1.20/M

Earlier MiniMax agent model for practical coding and productivity tasks

Open weightsModified MIT732/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot