AI TOOLS RADAR
Explore
All models / MINIMAX
M
minimax

MiniMax: H3

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...

View source on OpenRouter
Overview

Model specifications

Context
Not provided
Maximum output
Not provided
Architecture
text+image+audio+video->video
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
Capabilities

Input → Output

Input
textimagevideoaudio
Output
video
API

Supported API parameters

max_tokenstemperaturetop_p
Available providers

1 Provider

Minimax

unknown
Context
Not provided
Maximum output
Not provided
Input
Free
Output
Free
Cache read
Not provided
Cache write
Not provided
minimax

models

All models
Mminimax

MiniMax: Speech 2.8 HD

MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Context
Not provided
Input
text
Output
speech
Input: $100.00Output: Freeper 1M tokens
View model details →
Mminimax

MiniMax: Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Context
Not provided
Input
text
Output
speech
Input: $60.00Output: Freeper 1M tokens
View model details →