When was MiniMax H3 released?

MiniMax released MiniMax H3 on 31 Jul 2026. It is available through the Opper gateway.

Does MiniMax H3 support zero data retention?

No. The routes serving MiniMax H3 retain content; see the per-route data-handling section for each route's logging stance and retention window.

Where is MiniMax H3 hosted?

MiniMax H3 runs on US hosting routes through the Opper gateway.

Is MiniMax H3 trained on prompts and outputs?

Training behaviour varies by route. See the per-route data-handling section for each provider's training posture.

MiniMax H3

by MiniMax

Released 60 days after MiniMax M3 · Announcement · All MiniMax releases

MiniMax H3, also known as Hailuo 3.0, is the company's omni-modal video model released at the end of July 2026. It treats text, images, video, and audio as one shared context and generates clips of up to 15 seconds at 768p or 2K, with native stereo audio, spanning dialogue, effects, and room tone, produced in the same pass as the picture. Reference images let it carry specific subjects into a generation, and the audio-native design removes the separate sound stage most video pipelines still need. The model suits dialogue scenes, ads that depend on sound design, and multimodal briefs that mix text direction with visual references.

Call MiniMax H3 on Opper through POST /v3/videos. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Pricing

from $0.06 / sec

Billing

Usage-based

Released

31 Jul 2026

US residency available on fal

Pricing

Usage-based pricing, billed by usage and tiered by variant, not by token.

Variant	Price
2k	$0.13 / sec
768p	$0.06 / sec
reference_images_beyond_5	$0.08 / image

Available routes

MiniMax H3 runs on 2 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Price
fal	US		No	from $0.06 / sec
MiniMax	Multi		—	from $0.04 / image

Live routes and prices as JSON: api.opper.ai/v3/models?q=fal%2Fminimax-h3

Uptime and availability

One of MiniMax H3's 2 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

99.17%route uptime, last 30 days

Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route is not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting MiniMax H3 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

fal — United States🇺🇸

Content is retained: provider logging, 1-day retention. No training on customer data. US; SCCs.

Zero data retention: Retained: provider logging, 1-day retention.
Training: No training on customer data.
Logging: Other (1-day retention)
Abuse monitoring: On by default, holds flagged content
Transfer mechanism: SCCs

MiniMax — Multi-region

Content is retained: provider logging. Training posture pending review. GLOBAL; dpf sccs.

Zero data retention: Retained: provider logging.
Logging: Other
Abuse monitoring: On by default, holds flagged content
Transfer mechanism: dpf sccs

Get started

Call MiniMax H3 through the Opper gateway with one API key. Video models run on Opper's async video endpoint: POST /v3/videos answers 202 with a status URL, which you poll until the job is completed and then download the file from its url.

See the Opper video guide and the Opper multimodal skill.

MiniMax H3 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1# 1. Submit the job: answers 202 with an id and a status_url
2STATUS_URL=$(curl -s https://api.opper.ai/v3/videos \
3  -H "Authorization: Bearer $OPPER_API_KEY" \
4  -H "Content-Type: application/json" \
5  -d '{
6    "model": "fal/minimax-h3",
7    "prompt": "A paper boat drifting down a rain-soaked street at dusk",
8    "seconds": 5,
9    "resolution": "768p",
10    "aspect_ratio": "16:9",
11    "image": "https://example.com/first-frame.png"
12  }' | jq -r .status_url)
13
14# 2. Poll the status_url (GET /v3/artifacts/{id}/status) until "status"
15#    is "completed" (or "failed")
16curl "$STATUS_URL" -H "Authorization: Bearer $OPPER_API_KEY"
17
18# 3. Download the clip from the "url" in the completed status
19curl -o video.mp4 "<url>"