MiniMax chat, Hailuo video and music models

Explore/MiniMax Models

MiniMax API models

MiniMax chat, Hailuo video and music models

MiniMax is a multimodal AI provider covering text chat, Hailuo video generation, music generation, speech and image capabilities. PoYo.ai currently surfaces Hailuo video and MiniMax Music entries.

MiniMax models across chat, video, music and speech

Official MiniMax model coverage spans M2-series chat models, Hailuo video models, MiniMax Music models, Speech models and image generation capabilities.

On PoYo.ai, the current MiniMax provider page lists the MiniMax models that are available here now: Hailuo 02, Hailuo 2.3 and MiniMax Music 2.6. Use this page to compare video generation, image-to-video motion, song demos and creative audio workflows under the MiniMax provider.

Best-fit MiniMax API use cases

Chat, roleplay, long-context assistant and agent workflows with MiniMax M2 models
Text-to-video and image-to-video generation with Hailuo 02 and Hailuo 2.3
Music generation, song demos, background music and creative audio with MiniMax Music
Speech, voice and image workflows when those MiniMax models are available in your integration stack

API Docs

All models

6 Models

Text to Video

$0.105 / second

hailuo-03

MiniMax H3 (Hailuo 03) generates native 2K video from text, first/last frames, or image, video, and audio references.

Text to Video

$0.05 / second

h3-max

MiniMax H3 Max generates 5–15 second videos from text, first/last frames, or image, video and audio references at 480p, 768p and 1080p.

Text to Video

$0.025 / second

h3-max-turbo

MiniMax H3 Max Turbo generates 5–15 second videos from text or first/last frames at 480p, 768p and 1080p.

Music

$0.10 / generation

minimax-music-2.6

Generate complete songs from style prompts and lyrics with MiniMax Music 2.6. Supports vocal tracks, instrumental generation, prompt-driven lyrics optimization, and configurable audio output settings.

Text to Video

$0.035 / second

hailuo-02

MiniMax's #2 globally-ranked video model with NCR architecture, ultra-realistic physics, and 1080p cinematic output.

Text to Video

$0.175 / generation

hailuo-2.3

MiniMax's Hailuo 2.3 video model for realistic human motion, expressive characters, and text-to-video or first-frame guided generation at 768p and 1080p.

MiniMax Models API - pricing and performance

Run MiniMax models through PoYo.ai with transparent API pricing, model pages, and a consistent async generation workflow.

Transparent pricing

Each model page lists its current PoYo.ai API price and billing unit.

Model comparison

Compare task types, categories, and related providers before integration.

Async API workflow

Submit generation jobs and retrieve results through PoYo.ai model APIs.

Model	Category	Task types	Price
MiniMax H3 / Hailuo 03 hailuo-03	Video	Text to Video, Image to Video	$0.105Per second
MiniMax H3 Max h3-max	Video	Text to Video, Image to Video	$0.05Per second
MiniMax H3 Max Turbo h3-max-turbo	Video	Text to Video, Image to Video	$0.025Per second
MiniMax Music 2.6 minimax-music-2.6	Music	Music	$0.10Per generation
Hailuo 02 hailuo-02	Video	Text to Video, Image to Video	$0.035Per second
Hailuo 2.3 hailuo-2.3	Video	Text to Video, Image to Video	$0.175Per generation

Frequently asked questions

What MiniMax models are listed on PoYo.ai?+

PoYo.ai currently lists Hailuo 02, Hailuo 2.3 and MiniMax Music 2.6 under the MiniMax provider.

Does MiniMax only provide video and music models?+

No. Official MiniMax model coverage also includes M2-series chat models, speech models and image capabilities. This page reflects both the broader MiniMax ecosystem and the MiniMax models currently available on PoYo.ai.

Why is Hailuo included under MiniMax?+

Hailuo is MiniMax's video generation model line, so PoYo.ai groups Hailuo video models under the MiniMax provider instead of treating Hailuo as a separate supplier.