Skip to content
Pricing
MiniMax

MiniMax H3 API

Create videos with native audio using MiniMax H3. Start with text, first/last frames, or combined image, video and audio references. Available resolutions: 480P / 768P / 2K. 768P / 2K support 4–15 seconds; 480P starts at 5 seconds.

Modalities
TextImageVideoAudioVideo
Published
768P
$0.1/ second
Platform price · USD
2K
$0.12/ second
Platform price · USD
480P
$0.08/ second
Platform price · USD
Input
Native audioDescribe dialogue, ambience and music in the prompt.Included

480P starts at 5 seconds. Use 768P or 2K for 4-second clips or an AIGC watermark.

Request preview
{
  "model": "minimax-h3",
  "input": {
    "seconds": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "aigc_watermark": false,
    "prompt": "A breathtaking photorealistic science-fiction film shot for a premium AI technology platform. An immense elegant circular orbital observatory of brushed titanium and dark glass floats above the luminous blue curvature of a planet. A precisely engineered ring, fine panel seams, small warm windows and slender structural ribs; believable physical construction. The camera makes one slow smooth lateral orbit with subtle forward movement, creating clear parallax between the crisp station in the foreground and the planet below. A distant sun slowly emerges from behind the edge of the station, tracing a thin silver rim across the metal; clouds drift far below. Rich ink-blue space, delicate violet nebula wisps, restrained ice-blue atmosphere, silver and tiny warm highlights. Immediately compelling and clearly legible from the first frame. The entire main ring stays inside the central 70 percent of the frame with generous breathing room. Extremely crisp detailed metal, physically accurate light, controlled highlights, deep rich contrast, cinematic large-format photography. One continuous six-second shot, stable geometry, measured graceful motion. No cuts, no titles, no lettering, no logo, no watermark, no HUD, no interface, no particles flying toward the camera, no strobing, no explosive action, no excessive lens flare, no heavy motion blur. Landscape 16:9 composition."
  }
}
API keySign in to generate
Sign in to choose a key from your account.
Output
Example output
Open original

MiniMax H3 pricing

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

UsageQuantityRateCost
768P5 sec$0.1/ sec$0.5
Cost per request$0.5

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

View all specifications and prices
SpecificationOur priceOfficial reference
768P$0.1 / second
2K$0.12 / second
480P$0.08 / second

See what it can create.

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

Orbital sunrise

View prompt

A breathtaking photorealistic science-fiction film shot for a premium AI technology platform. An immense elegant circular orbital observatory of brushed titanium and dark glass floats above the luminous blue curvature of a planet. A precisely engineered ring, fine panel seams, small warm windows and slender structural ribs; believable physical construction. The camera makes one slow smooth lateral orbit with subtle forward movement, creating clear parallax between the crisp station in the foreground and the planet below. A distant sun slowly emerges from behind the edge of the station, tracing a thin silver rim across the metal; clouds drift far below. Rich ink-blue space, delicate violet nebula wisps, restrained ice-blue atmosphere, silver and tiny warm highlights. Immediately compelling and clearly legible from the first frame. The entire main ring stays inside the central 70 percent of the frame with generous breathing room. Extremely crisp detailed metal, physically accurate light, controlled highlights, deep rich contrast, cinematic large-format photography. One continuous six-second shot, stable geometry, measured graceful motion. No cuts, no titles, no lettering, no logo, no watermark, no HUD, no interface, no particles flying toward the camera, no strobing, no explosive action, no excessive lens flare, no heavy motion blur. Landscape 16:9 composition.

What is MiniMax H3?

Create videos with native audio using MiniMax H3. Start with text, first/last frames, or combined image, video and audio references. Available resolutions: 480P / 768P / 2K. 768P / 2K support 4–15 seconds; 480P starts at 5 seconds.

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.

Image references

Use up to 9 images to guide subjects, composition and style. References guide the content without fixing the first frame.

Video references

Use up to 3 clips to guide motion and camera behavior; combine them with image references.

Audio references

Use up to 3 audio clips to guide sound. At 480P, also supply an image or video reference.

MiniMax H3 specifications

Model IDminimax-h3
ProviderMiniMax
API/v1/tasks
Resolution480P / 768P / 2K
Aspect ratio21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16
Duration4–15 seconds
Reference imagesUp to 9
Frame imagesUp to 2
Reference videosUp to 3
Reference audioUp to 3

Supported combinations and limits

  • The 768P and 2K routes support 4–15 seconds. The 480P route starts at 5 seconds and does not support the AIGC watermark.
  • Image, video and audio references can be combined. They cannot be mixed with start/end frame inputs.
  • At 480P, use at most 12 references in total. Audio requires an image or video reference. Each video or audio clip is 2–15 seconds, with at most 15 seconds total per type.
  • H3 generates native audio. Direct dialogue, ambience and music through the prompt; this platform does not expose an audio toggle.
  • The public frame array requires a start image. An end-frame-only input and video extension are not exposed.
Capability check · 2026-09-07MiniMax · official V2 API ↗

Compare MiniMax H3 with related models

SpecificationMiniMax H3MiniMax H3 Max Turbo
ProviderMiniMaxMiniMax
Input → outputTextImageVideoAudioVideoTextImageVideo
Start / end framesSupported · 1 or 2 imagesSupported · 1 or 2 images
Reference videos3
Reference audio3
Selection basisCurrent modelBoth declare text, image input · Same billing units
Resolution480P / 768P / 2K480P / 768P
Reference images9
Starting price$0.08 / second$0.05 / 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 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.

  1. 01
    Get your API key

    Sign in and prepare a key with access to this model.

  2. 02
    Configure your request

    Choose parameters in Playground and copy the API example.

  3. 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",
  "input": {
    "seconds": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "aigc_watermark": false,
    "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",
    "input": {
      "seconds": 5,
      "resolution": "480P",
      "aspect_ratio": "16:9",
      "aigc_watermark": false,
      "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\",\"input\":{\"seconds\":5,\"resolution\":\"480P\",\"aspect_ratio\":\"16:9\",\"aigc_watermark\":false,\"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

ParameterTypeValues & constraints
audiosarray
imagesarray
prompt *string
videosarray
secondsintegerDefault: 5
resolutionJSON"480P" · "768P" · "2K"Default: "480P"
aspect_ratioJSON"21:9" · "16:9" · "4:3" · "1:1" · "3:4" · "9:16"Default: "16:9"
frames_imagesarray
aigc_watermarkbooleanDefault: false
Full JSON Schema and combination constraints
{
  "type": "object",
  "allOf": [
    {
      "not": {
        "required": [
          "frames_images",
          "images"
        ]
      }
    },
    {
      "not": {
        "required": [
          "frames_images",
          "videos"
        ]
      }
    },
    {
      "not": {
        "required": [
          "frames_images",
          "audios"
        ]
      }
    }
  ],
  "required": [
    "prompt"
  ],
  "properties": {
    "audios": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 3,
      "minItems": 1
    },
    "images": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 9,
      "minItems": 1
    },
    "prompt": {
      "type": "string",
      "maxLength": 7000,
      "minLength": 1
    },
    "videos": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 3,
      "minItems": 1
    },
    "seconds": {
      "type": "integer",
      "default": 5,
      "maximum": 15,
      "minimum": 4
    },
    "resolution": {
      "enum": [
        "480P",
        "768P",
        "2K"
      ],
      "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
    },
    "aigc_watermark": {
      "type": "boolean",
      "default": false
    }
  },
  "additionalProperties": false
}

MiniMax H3 API · Common questions

Answers about pricing, inputs, integration and results.

How much does MiniMax H3 cost?

The current public price starts at $0.08 / 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: audios, images, prompt, videos, seconds, resolution, aspect_ratio, frames_images, aigc_watermark. The parameter table includes allowed values and defaults.

Can I use reference images?

Yes. Use the reference mode to upload images or supply their URLs. The current limit is 9 images. Reference images guide a new generation; they do not imply mask editing support.

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 ↗