MiniMax H3 Max Turbo API

Create 5–15 second videos with MiniMax H3 Max Turbo from text, a start image, or first and last frames. Available resolutions: 480P / 768P. Frame-based output follows the start image; general image, video and audio references are not supported.

Modalities

TextImageVideo

Published

480P

$0.05/ second

$0.025 · official reference

768P

$0.08/ second

$0.04 · official reference

Input

Generation mode480P · $0.05 / secondPrompt 75 / 50,000

resolutionaspect ratio

Duration5–15 seconds

Request preview

{
  "model": "minimax-h3-max-turbo",
  "input": {
    "seconds": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "prompt": "清晨薄雾中的山间湖泊，一只白色纸船缓慢漂过水面，留下细小涟漪。镜头贴近水面平稳向前推进，阳光逐渐照亮远处山峰，电影质感，一个连续镜头，无文字，无字幕。"
  }
}

API keySign in to generate

API key for this model

Output

Example output

Open original ↗

Build with this model

The example follows your Playground parameters.

curl --request POST 'https://newrouters.com/v1/tasks' \
  --header 'Content-Type: application/json' \
  --header "Authorization: Bearer $MODEL_API_KEY" \
  --data '{
  "model": "minimax-h3-max-turbo",
  "input": {
    "seconds": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "prompt": "清晨薄雾中的山间湖泊，一只白色纸船缓慢漂过水面，留下细小涟漪。镜头贴近水面平稳向前推进，阳光逐渐照亮远处山峰，电影质感，一个连续镜头，无文字，无字幕。"
  }
}'

Set MODEL_API_KEY in your environment. Keep your secret key on the server. Full documentation ↗

MiniMax H3 Max Turbo pricing

Estimate one request, then choose a budget for your workflow.

SpecificationDuration · seconds

Usage	Quantity	Rate	Cost
480P	5 sec	$0.05/ sec	$0.25

Cost per request$0.25

Public USD estimate. Your account rate and final recorded usage determine the actual charge.

View all specifications and prices

Specification	Our price	Official reference
480P	$0.05 / second	$0.025
768P	$0.08 / second	$0.04

Related models

Video models ↗

Model	Price	Resolution	Input → output
MiniMaxMiniMax H3 Max TurboCurrent	$0.05 / second	480P / 768P	TextImageVideo
MiniMaxMiniMax H3Both declare text, image inputSame billing units	$0.08 / second	480P / 768P / 2K	TextImageVideoAudioVideo

See what it can create.

Existing examples generated through the platform, with original media and prompts.

Paper boat on a misty lake

View prompt

清晨薄雾中的山间湖泊，一只白色纸船缓慢漂过水面，留下细小涟漪。镜头贴近水面平稳向前推进，阳光逐渐照亮远处山峰，电影质感，一个连续镜头，无文字，无字幕。

Original media ↗Try this prompt ↗

What is MiniMax H3 Max Turbo?

Text to video

Describe the scene, subject movement and camera direction. Select the duration, resolution and aspect ratio.

Animate a start frame

Upload one image to define the opening shot. The prompt directs the movement that follows; the output ratio follows this image.

First and last frames

Provide two images in order: start, then end. The model generates the motion connecting these frames.

MiniMax H3 Max Turbo specifications

Model ID	minimax-h3-max-turbo
Provider	MiniMax
API	/v1/tasks
Resolution	480P / 768P
Aspect ratio	21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16
Duration	5–15 seconds
Frame images	Up to 2

Supported combinations and limits

Supports text, a start frame, or a start/end pair. General reference images, reference video and reference audio are not exposed for this model.
Generate 5–15 seconds at 480P or 768P. Aspect ratio is selectable only for text-to-video; frame generation follows the start image.
No audio switch, seed, camera-fixed switch or video-extension endpoint is exposed by the current platform contract.

Capability check · 2026-09-07fal · text to video ↗fal · image to video ↗

Compare MiniMax H3 Max Turbo with related models

Specification	MiniMax H3 Max Turbo	MiniMax H3
Provider	MiniMax	MiniMax
Input → output	TextImageVideo	TextImageVideoAudioVideo
Start / end frames	Supported · 1 or 2 images	Supported · 1 or 2 images
Reference videos	—	3
Reference audio	—	3
Selection basis	Current model	Both declare text, image input · Same billing units
Resolution	480P / 768P	480P / 768P / 2K
Reference images	—	9
Starting price	$0.05 / second	$0.08 / second

Choose by the input types, output settings and billing unit your workflow needs. Try the same prompt across models to compare results for your own use case.

BUILD WITH NEWROUTERS

Build with MiniMax H3 Max Turbo in your app

Submit parameters through the Media Tasks API, then retrieve the result with the task ID. Image and video models keep their own input requirements.

01
Get your API key
Sign in and prepare a key with access to this model.
02
Configure your request
Choose parameters in Playground and copy the API example.
03
Run and inspect the result
Review status, outputs and charges in History.

API integration

POST /v1/tasks · Authorization: Bearer

cURL

curl 'https://newrouters.com/v1/tasks' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  --data '{
  "model": "minimax-h3-max-turbo",
  "input": {
    "seconds": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "prompt": "A quiet mountain lake at sunrise, soft morning light."
  }
}'

JavaScript

const response = await fetch("https://newrouters.com/v1/tasks", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer $MODEL_API_KEY"
  },
  body: JSON.stringify({
    "model": "minimax-h3-max-turbo",
    "input": {
      "seconds": 5,
      "resolution": "480P",
      "aspect_ratio": "16:9",
      "prompt": "A quiet mountain lake at sunrise, soft morning light."
    }
  })
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.text());

Python

import json
import requests

response = requests.post(
    "https://newrouters.com/v1/tasks",
    headers=json.loads("{\"Content-Type\":\"application/json\",\"Authorization\":\"Bearer $MODEL_API_KEY\"}"),
    json=json.loads("{\"model\":\"minimax-h3-max-turbo\",\"input\":{\"seconds\":5,\"resolution\":\"480P\",\"aspect_ratio\":\"16:9\",\"prompt\":\"A quiet mountain lake at sunrise, soft morning light.\"}}"),
    timeout=300,
)
response.raise_for_status()
print(response.text)

Poll the returned task ID for processing status and output assets.

curl -H "Authorization: Bearer $MODEL_API_KEY" "https://newrouters.com/v1/tasks/$TASK_ID"

Documentation: Authentication · Task status and results · Error handling

Full API parameters and combination constraints

Request parameters

Parameter	Type	Values & constraints
`prompt` *	string
`seconds`	integer	Default: 5
`resolution`	JSON	"480P" · "768P"Default: "480P"
`aspect_ratio`	JSON	"21:9" · "16:9" · "4:3" · "1:1" · "3:4" · "9:16"Default: "16:9"
`frames_images`	array

Full JSON Schema and combination constraints

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 50000,
      "minLength": 1
    },
    "seconds": {
      "type": "integer",
      "default": 5,
      "maximum": 15,
      "minimum": 5
    },
    "resolution": {
      "enum": [
        "480P",
        "768P"
      ],
      "default": "480P"
    },
    "aspect_ratio": {
      "enum": [
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16"
      ],
      "default": "16:9"
    },
    "frames_images": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 2,
      "minItems": 1
    }
  },
  "additionalProperties": false
}

MiniMax H3 Max Turbo API · Common questions

Answers about pricing, inputs, integration and results.

How much does MiniMax H3 Max Turbo cost?

The current public price starts at $0.05 / second. The pricing section lists each specification. Playground checks your account price before submitting; the completed request records the final charge.

How do I get a NewRouters API key?

Sign in and open Quick Start above the workspace. Select or create a key with access to this model, then copy the request example.

Which inputs and output settings are supported?

Supported input fields: prompt, seconds, resolution, aspect_ratio, frames_images. The parameter table includes allowed values and defaults.

Can I use reference images?

This model accepts frame images. Use start-frame mode for one image, or first-and-last-frame mode for two images. These define the video frames, unlike general reference images.

How do I retrieve results and past requests?

Save the returned task ID and query the task until it succeeds or fails. The History tab lets you reopen your tasks and reuse their parameters.

What happens if the model is closed?

The model keeps its page and identity, but new generation requests are blocked. Existing task records remain accessible. An upstream outage is reported separately from an administrator closing the model.

Read the API documentation ↗

Discover more AI tools

Browse all models ↗

Integration topics / Documentation

All documentation ↗

QUICK STARTHello, API.

Docs: From API key to your first request

Set up authentication, select a model and run your first request.

View docs section ↗

MEDIA API/v1/tasks

Docs: Create tasks and retrieve outputs

Understand task states, output URLs and the generation lifecycle.

View docs section ↗

INTEGRATION{ your next idea }

Docs: Choose your first request endpoint

Choose the right endpoint and verify current models and parameters.

View docs section ↗

MiniMax H3 Max Turbo API

Build with this model

MiniMax H3 Max Turbo pricing

See what it can create.

Paper boat on a misty lake

What is MiniMax H3 Max Turbo?

Text to video

Animate a start frame

First and last frames

MiniMax H3 Max Turbo specifications

Supported combinations and limits

Compare MiniMax H3 Max Turbo with related models

Build with MiniMax H3 Max Turbo in your app

API integration

Request parameters

MiniMax H3 Max Turbo API · Common questions

How much does MiniMax H3 Max Turbo cost?

How do I get a NewRouters API key?

Which inputs and output settings are supported?

Can I use reference images?

How do I retrieve results and past requests?

What happens if the model is closed?

Discover more AI tools

AI image generator

AI video generator

AI chat API

API documentation

Integration topics / Documentation

Docs: From API key to your first request

Docs: Create tasks and retrieve outputs

Docs: Choose your first request endpoint