H3 Max Image to Video

fal/minimax/h3-max/image-to-video

videoContext —

fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

Price

Price$0.0325

per second

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

Provider	Tag	Quant	Input	Output	Context	Uptime	Status	Source
fal	—	—	Not published—	Not published—	—	—	Listed	fal

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

Input tokens Output tokens Units

$32.50 at list price for this workload

Every rate

Unit	Input	Output	Flat	Confidence
second	Not published—	Not published—	$0.0325/second	official

Price history

H3 Max Image to Video

input or flat output

H3 Max Image to Video

input or flat output

Daily snapshots

UTC date	Unit	Input	Output	Flat
2026-10-08	seconds	Not published—	Not published—	$0.03
2026-10-09	second	Not published—	Not published—	$0.03
2026-10-10	second	Not published—	Not published—	$0.03
2026-10-11	second	Not published—	Not published—	$0.03
2026-10-12	second	Not published—	Not published—	$0.03
2026-10-13	second	Not published—	Not published—	$0.03
2026-10-14	second	Not published—	Not published—	$0.03
2026-10-15	second	Not published—	Not published—	$0.03
2026-10-16	second	Not published—	Not published—	$0.0325
2026-10-17	second	Not published—	Not published—	$0.0325
2026-10-18	second	Not published—	Not published—	$0.0325
2026-10-19	second	Not published—	Not published—	$0.0325
2026-10-20	second	Not published—	Not published—	$0.0325
2026-10-21	second	Not published—	Not published—	$0.0325
2026-10-22	second	Not published—	Not published—	$0.0325
2026-10-23	second	Not published—	Not published—	$0.0325
2026-10-24	second	Not published—	Not published—	$0.0325
2026-10-25	second	Not published—	Not published—	$0.0325
2026-10-26	second	Not published—	Not published—	$0.0325
2026-10-27	second	Not published—	Not published—	$0.0325
2026-10-28	second	Not published—	Not published—	$0.0325
2026-10-29	second	Not published—	Not published—	$0.0325
2026-10-30	second	Not published—	Not published—	$0.0325

Alternatives

MiniMax H3 Max Text to Video$0.0325/second · Compare
Gemini Omni Flash 1.1 Image to Video$0.03/second · Compare
Qwen: Qwen3.7 Flash$0.03/1M · Compare
Seedance 2.5 US Image to Video$0.0214/1000 tokens · Compare
Seedance 2.5 US Reference to Video$0.0214/1000 tokens · Compare
FLUX 3 Max Image to Video$0.0213/second · Compare

Call this model

OpenRouter id fal/minimax/h3-max/image-to-video. InferenceList does not send the request.

curl

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"fal/minimax/h3-max/image-to-video","messages":[{"role":"user","content":"Hello"}]}'

JavaScript

await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "fal/minimax/h3-max/image-to-video",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python

import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "fal/minimax/h3-max/image-to-video", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON