Multimodal MiniMax Open Models Creative Tools Model serving Inference Optimization Benchmarks

MiniMax H3

Open-weight video generation model

An open-weight generative video model release from MiniMax, announced with downloadable Hugging Face weights and deployment endpoints.

Pricing

Model profile · Current snapshot

Input / 1M

$0.15

Output / 1M

$0.60

Blended / 1M

$0.262

Output TPS

118

TTFT (s)

0.74

Model Intelligence

Arena ranking

Benchmarkable

Yes

Model level

release

Intelligence Index

28.9

HLE

0.48

SciCode

0.53

LCR

0.8

Recent stories

3 linked stories

releaseSECONDARY2026-10-20

FastVideo claims FastH3 Omni cuts video generation latency 12×

FastVideo releases FastH3 Omni weights and training code, claiming 12× lower latency than base MiniMax-H3. The comparison covers 27 matched workloads on eight GB200 GPUs, and ComfyUI support is available.

releasePRIMARY2026-08-03

MiniMax H3 releases Hugging Face weights and fal video endpoints

MiniMax H3 now has Hugging Face weights, fal endpoints, AI Toolkit LoRA support, and reported single-RTX-5090 local runs. MiniMax also said deployment in the US, EU, UK, and South Korea is available through formal authorization.

releasePRIMARY2026-07-30

MiniMax launches H3 for video apps and APIs

MiniMax announced H3 for app and API access, with OpenRouter, Vercel, Pika, fal, Runway, and Venice integrations. Artificial Analysis ranked it No. 1 for video editing, and MiniMax said open weights are planned.