MiniMax H3 Text-to-Video API

MiniMax H3 is a general-purpose, omni-modal video generation model released by MiniMax in July 2026. It generates high-quality videos from multimodal content (text, images, video, and audio). This document covers its Text-to-Video capability: generating video from a text prompt alone, with 2K direct output, native stereo audio, and optional multimodal reference, served through an out-of-the-box REST inference API.

Model Positioning

MiniMax H3 Text-to-Video targets video creation workflows that start from text. It is the text-to-video endpoint of the H3 omni-modal generation system. Unlike the Image-to-Video endpoint, it requires no reference images — a text prompt alone produces a video with native stereo audio, ideal for purely creative, reference-free tasks. For first/last-frame control or image animation, use the Image-to-Video endpoint.

Core Capabilities

2K direct output

Native 2K (2160P) resolution output, not upscaled; a 768P tier is also available to control cost. Both tiers are billed per output duration.

Native stereo audio

24 FPS cinematic frame rate with 32 kHz stereo audio generated in sync with the visuals — dialogue, sound effects, and ambient audio produced in one pass, no separate dubbing needed.

Complex prompt adherence

The model understands long, multi-layered prompts covering subject, scene, composition, camera movement, lighting, and style, making it suitable for cinematic trailers, ad storyboards, and other creative generation.

Multimodal extension

The content array of the Text-to-Video endpoint supports four element types — text / image_url / video_url / audio_url — allowing optional reference materials (style images, reference videos, reference audio) alongside the text prompt for style transfer and content consistency.

Asynchronous task queue

Standard three-step flow: submit task → query status → get result, suitable for long-running jobs and batch production.

Pricing

Total = unit price × output video duration. Billed by actual generated duration with no minimum-length threshold.

Use Cases

• Cinematic trailers and storyboards: generate film segments with native stereo audio from text alone
• Advertising and brand assets: quickly produce dynamic ad previews with controlled per-clip cost
• Short-video and social content: batch text-to-video production across multiple aspect ratios
• Creative concept validation: turn text directly into video without photography or 3D modeling
• Game assets and dynamic posters: stylized scene generation with 2K high-definition delivery

Model Comparison

MiniMax H3 Text-to-Video vs. H3 Image-to-Video

MiniMax H3 Text-to-Video vs. Hailuo 2.3 and Hailuo 02

Note: Hailuo 2.3 is billed per video (domestic list price from 2 CNY per clip), while the H3 series is billed per second; convert by total duration when comparing unit prices directly.

Why Choose MiniMax H3 Text-to-Video?

• 2K direct output + native stereo audio: visuals and sound generated in one pass, no upscaling or dubbing
• Text-driven only: no reference assets to prepare — one prompt, one video
• Transparent per-second billing: unit price × duration, predictable cost with no hidden fees
• Long-prompt adherence: stable results for complex, multi-layered instructions
• Open ecosystem: built on 33B open-sourced weights, deployable locally or customizable

API

This interface is an asynchronous task-based REST API. Submit endpoint: https://api.icreat.ai/v1/task/submit/minimax/h3-video/text-to-video. The flow has three steps: POST the task parameters to the submit endpoint and receive a task_id; poll the query endpoint with the task_id until the status is SUCCEEDED; then call the result endpoint to fetch the generated video. A callback_url can also be provided to receive task status-change notifications.

Key request parameters: content (multimodal input array; must include a non-empty text item as the prompt, with optional image_url / video_url / audio_url reference materials), resolution (768P or 2K), duration (integer 4–15), ratio (aspect ratio, default adaptive), callback_url (optional callback address), and aigc_watermark (optional AIGC watermark toggle, default false).

Specifications

Architecture

MiniMax H3 Text-to-Video uses an asynchronous task-queue architecture. Requests enter the task queue via the submit endpoint and are processed by the H3 omni-modal generation system (Context-IR instruction understanding + H3-VAE + H3-Omni Transformer + In-context Regeneration). The system first distills the input instructions into a context intermediate representation, then generates a video frame sequence with native stereo audio guided by optional reference materials, finally outputting at 2K or 768P. Task status and results are queried through dedicated endpoints, naturally supporting high-concurrency batch calls.

Notes

• duration must be an integer between 4 and 15; out-of-range values return an error
• content must contain a non-empty text item (prompt is required)
• ratio is required in text-to-video mode; when not specified it defaults to adaptive, letting the system pick the most suitable aspect ratio
• The 2K tier costs more per second than 768P; estimate cost in advance for long videos (total = unit price × duration)
• Fetch results via the result endpoint promptly after completion; result retention period is subject to the platform
• Multimodal reference materials (images/videos/audio) are optional and used for style or consistency guidance; not every item will be fully preserved

FAQ

What is the difference between MiniMax H3 Text-to-Video and Image-to-Video?

Both belong to the H3 series and share the same resolution (768P/2K), duration (4–15 seconds), and asynchronous task flow. The difference is input: Text-to-Video takes only a text prompt (with optional reference materials), ideal for creative generation without reference visuals; Image-to-Video requires images (first or first/last frame) and animates them, with precise first/last-frame control.

Can Text-to-Video include reference images?

Yes. The content array supports image_url / video_url / audio_url elements as optional reference materials for style transfer or content consistency. However, precise first/last-frame control is an Image-to-Video capability — Text-to-Video does not support first_frame / last_frame role annotations.

How is billing calculated?

Billed by output duration: total = unit price × output video duration. 768P is $0.10/sec and 2K is $0.14/sec; a 5-second clip costs $0.50 and $0.70 respectively.

What happens if I don't specify ratio?

It defaults to adaptive, where the system automatically selects the most suitable aspect ratio based on the input. If you have a specific aspect-ratio requirement, specify it explicitly.