models/MiniMax/H3 Max Extend Video
MiniMax

H3 Max Extend Video

video
Compare

H3 Max Extend Video adds a text-guided continuation to an existing video. It supports prompt expansion, adjustable duration and aspect ratio, and output resolutions from 480p to 2K, returning either the full extended video or only the new footage.

MODALITIES
video
PER SECOND
$0.050

H3 Max Extend Video (minimax/h3-max/extend-video) is a video model from MiniMax. Pricing via AIgateway: $0.050 per second. Call it via https://api.aigateway.sh/v1/videos/generations — set model="minimax/h3-max/extend-video".

model · minimax/h3-max/extend-video

Use this model

model: minimax/h3-max/extend-video
curl https://api.aigateway.sh/v1/videos/generations \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/h3-max/extend-video","prompt":"a slow drone shot over a mountain lake","duration":5}'

Capabilities

Video to video

Pricing

Per video second$0.050
You pay pass-through pricing.
See API example →CompareAPI referenceSee usage ranking →

Collections

More video models →More from MiniMax →Frontier models →Free-tier models →
API schema

Call H3 Max Extend Video from any OpenAI SDK

POST https://api.aigateway.sh/v1/videos/generations·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "minimax/h3-max/extend-video",
  "prompt": "A drone shot of a mountain lake at golden hour",
  "duration": 5,  // seconds
  "aspect_ratio": "16:9"
}
// optional "image_url" to animate a seed image

// Response is an async job — poll /v1/jobs/<id> until status === "completed".

Response

json
{
  "id": "job_abc123",
  "status": "queued",        // queued | processing | completed | failed
  "model": "minimax/h3-max/extend-video",
  "created": 1776947082
}

// After completion:
{
  "id": "job_abc123",
  "status": "completed",
  "result": {
    "url": "https://media.aigateway.sh/video/abc123.mp4",
    "duration": 5,
    "resolution": "1920x1080"
  }
}

Quickstart

import os, requests

r = requests.post(
    "https://api.aigateway.sh/v1/videos/generations",
    headers={"Authorization": f"Bearer {os.environ['AIGATEWAY_API_KEY']}"},
    json={
        "model": "minimax/h3-max/extend-video",
        "prompt": "A drone shot of a mountain lake",
        "duration": 5,
        "aspect_ratio": "16:9"
    },
)
print(r.json())

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is H3 Max Extend Video?
H3 Max Extend Video adds a text-guided continuation to an existing video. It supports prompt expansion, adjustable duration and aspect ratio, and output resolutions from 480p to 2K, returning either the full extended video or only the new footage. It is a video model from MiniMax, accessible via AIgateway's OpenAI-compatible API at slug minimax/h3-max/extend-video.
How much does H3 Max Extend Video cost via AIgateway?
Pass-through pricing. See the pricing panel on this page for exact rates.
How do I call H3 Max Extend Video from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "minimax/h3-max/extend-video". The request and response shapes match OpenAI exactly.
Does H3 Max Extend Video support streaming, tool calling, vision, and JSON mode?
Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
Can I bring my own MiniMax API key (BYOK)?
Yes. Attach a MiniMax key in your AIgateway dashboard and this model flips to pass-through — you pay MiniMax directly and AIgateway adds no platform fee on those calls.