How is the minimax-h3-max API billed?

minimax-h3-max is pay-as-you-go from ¥0.264 from / s. The rate depends on output resolution (480p / 768p) and whether video input is included; see the pricing table on this page. Billed at EasyAPI's public price, no subscription required.

How do I call minimax-h3-max through the API?

EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to minimax/minimax-h3-max, then send requests to /v1/videos. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.

Which video generation parameters does minimax-h3-max support?

prompt, duration, resolution (480p / 768p), aspect_ratio, generate_audio, seed and input_references (first frame, last frame, reference video and audio) for text-to-video and image-to-video. See the Parameters table on this page for details.

How do I get started with minimax-h3-max?

Sign up for EasyAPI, create an API key in the console and top up your balance to call minimax-h3-max pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

minimax-h3-max

Name: minimax-h3-max
Brand: MiniMax
Price: 0.264 CNY
Availability: InStock

Video

Minimax-H3 ultra-fast generation version. Supports only text-to-video and image-to-video (first frame / last frame); intermediate frames and multimodal references (reference image / reference video / reference audio) are not supported. Resolutions 480P / 768P, no 2K support; duration 5-15 seconds.

Resolution

480p

768p

Without video input

20% off

¥0.264/ sMarket: ¥0.33

¥0.4/ sMarket: ¥0.5

Image input ¥0.4/ image Market: ¥0.5

With video input

20% off

¥0.296/ sMarket: ¥0.37

¥0.776/ sMarket: ¥0.97

Input

Text / Image

Output

Video

Input

Video script *

Exact size

Seed

Use -1 for random; identical seeds are not guaranteed to match

Duration 5

415

生成视频时长（秒），取值范围4–15

Resolution

输出分辨率，计费档位由请求分辨率决定

Aspect ratio

画幅比例；文生视频支持 21:9/16:9/4:3/1:1/3:4/9:16（默认 16:9），不支持 adaptive；图生视频忽略该参数；本模型不支持参考生视频。

Optional. Slots follow the model's input_references declaration; upload a local file or paste a public URL.

First frame imageimage · first_frame

Click to upload

Last frame imageimage · last_frame

Click to upload

Last frame requires a first frame URL

Output

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token

shell

export EASYAPI_API_KEY=sk-xxxxxxxx

Make your first request

Use minimax/minimax-h3-max with the EasyAPI API:

cURL

curl https://token.easyapi.com/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{
  "model": "minimax/minimax-h3-max",
  "prompt": "A cute baby sea otter",
  "duration": 5,
  "resolution": "2K",
  "aspect_ratio": "16:9",
  "input_references": [
    {
      "role": "first_frame",
      "type": "image",
      "url": "https://cdn.example.com/reference.jpg"
    }
  ]
}'

Endpoint

Submits a video generation task from a text prompt.

POSThttps://token.easyapi.com/v1/videos

Authorization: Bearer $EASYAPI_API_KEY
Content-Type: application/json
Model: minimax/minimax-h3-max

Submit a video generation task from a prompt. The response includes a task ID or result URL. Docs

Parameters

Name	Type	Required	Default	Description
`model`	string	Yes	—	Model ID, e.g. bytedance/seedance-2.0. Currently minimax/minimax-h3-max
`aspect_ratio`	string	No	16:9	画幅比例；文生视频支持 21:9/16:9/4:3/1:1/3:4/9:16（默认 16:9），不支持 adaptive；图生视频忽略该参数；本模型不支持参考生视频。；可选：16:9 / 21:9 / 4:3 / 1:1 / 3:4 / 9:16
`duration`	integer	No	5	生成视频时长（秒），取值范围4–15；范围：4 ~ 15
`input_references`	array	No	—	首尾帧素材：图生视频用 first_frame/last_frame；本模型不支持参考图/视频/音频。
`input_references[].role`	string	Yes	—	素材用途：first_frame 首帧、last_frame 尾帧；可选：first_frame / last_frame
`input_references[].type`	string	Yes	—	引用素材类型；本模型只支持图片首/尾帧；可选：image
`input_references[].url`	string	Yes	—	素材地址：HTTPS URL、data URL 或裸 base64（不含 data: 前缀）
`prompt`	string	Yes	—	文本提示词，去除首尾空格后长度不超过7000字符；参考生视频中按 Image 1、Video 1 等引用素材；最大长度：7000
`resolution`	string	No	2K	输出分辨率，计费档位由请求分辨率决定；可选：2K / 768P
`webhook_url`	string	No	—	任务状态变化时接收 FAL 格式回调的 HTTPS 地址，也可通过查询参数 fal_webhook 指定

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

minimax-h3-max FAQ

How is the minimax-h3-max API billed?: minimax-h3-max is pay-as-you-go from ¥0.264 from / s. The rate depends on output resolution (480p / 768p) and whether video input is included; see the pricing table on this page. Billed at EasyAPI's public price, no subscription required.
How do I call minimax-h3-max through the API?: EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to minimax/minimax-h3-max, then send requests to /v1/videos. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.
Which video generation parameters does minimax-h3-max support?: prompt, duration, resolution (480p / 768p), aspect_ratio, generate_audio, seed and input_references (first frame, last frame, reference video and audio) for text-to-video and image-to-video. See the Parameters table on this page for details.
How do I get started with minimax-h3-max?: Sign up for EasyAPI, create an API key in the console and top up your balance to call minimax-h3-max pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

Related models

All models

minimax-h3

MiniMax

Lightweight open-weights video generation model supporting instruction-based editing, text and brand rendering, and video motion transfer, natively outputting visuals and audio track, built for advertising and e-commerce creative scenarios.

Video

20% off

Resolution	Output price
2k	¥0.64/ s
768p	¥0.4/ s
Image input	¥0.16/ image

happyhorse-1.1-i2v

Alibaba

HappyHorse-1.1-I2V支持图生视频，进一步提升画面质感、动态表现与跨片段一致性。模型能够更精准地理解输入图像并延续创作意图，在人物皮肤质感、ID跨片段保持、动作流畅度、文字渲染稳定性以及音画同步上带来显著改善，输出更真实自然、细节丰富且一致性更高的高质量视频。

视频

60% off

Resolution	Output price
480p	¥0.18/ s
720p	¥0.36/ s
1080p	¥0.48/ s

happyhorse-1.1-r2v

Alibaba

HappyHorse-1.1-R2V支持参考生视频，进一步提升主体、场景风格与画面一致性的稳定保持。模型最多支持9张参考图片输入，能够更精准理解并延续创作意图，在人物、场景、风格和镜头表现上带来更强的可控性与表现力。

视频

60% off

Resolution	Output price
480p	¥0.18/ s
720p	¥0.36/ s
1080p	¥0.48/ s

happyhorse-1.1-t2v

Alibaba

HappyHorse-1.1-T2V支持文生视频，进一步提升文本语义理解、镜头调度与动态生成表现。模型能够更精准地还原创作意图，在人物动作、场景氛围、视觉美感和物理运动上生成更流畅自然、细节丰富且一致性更高的高质量视频。

视频

60% off

Resolution	Output price
480p	¥0.18/ s
720p	¥0.36/ s
1080p	¥0.48/ s

Input

Output

Input

Output

Get your API key

Make your first request

Endpoint

Parameters

Using third-party SDKs

minimax-h3-max FAQ

Related models

Popular comparisons for minimax-h3-max