MiniMax H3 Max API

MiniMax · video model page

What MiniMax H3 Max is

MiniMax’s video-generation documentation describes MiniMax H3 Max as a high-speed video model post-trained on MiniMax H3, jointly offered with fal.ai. It supports text-to-video, image-to-video (first / last frame), and reference generation, with 480P or 768P output and 5–15 second clips at 24 fps. The vendor API model name is MiniMax-H3-Max.

fal’s August 2026 post introduces H3 Max as a post-trained variant optimized for throughput, and lists hosted endpoints under minimax/h3-max. This page covers the H3 Max video root, not MiniMax chat models such as M3.1 Flash. bnrouter does not invent a gateway model id or a price for this page.

Official announcement: Read MiniMax’s video generation guide

Where developers can use it

MiniMax and fal list these official surfaces first. bnrouter is an optional OpenAI-compatible gateway in front of connected upstream accounts.

MiniMax API video generation (model name MiniMax-H3-Max), as documented by MiniMax
fal playground and API for H3 Max, as described in fal’s August 2026 announcement
Hosted fal minimax/h3-max endpoints
bnrouter, if the operator has connected an upstream that serves this model. The plaza may still show coming soon — confirm the id in the console or GET /v1/models.

How to call it through bnrouter

bnrouter is an OpenAI-compatible AI API gateway. Create an API key in the console, then send requests to the gateway base URL. Chat completions may not be the right request shape for image or video generation — see the Image & video API docs for the images format this site already documents. This repository does not yet record a gateway model id — copy the id shown in the console (or from GET /v1/models) into the model field. The plaza listing may still show coming soon.

Подключение к bnrouter

Base URL · OpenAI SDK: https://console.bnrouter.com/v1
Адрес чата: POST https://console.bnrouter.com/v1/chat/completions

Укажите этот Base URL в OpenAI-совместимом SDK. Он уже включает /v1. Используйте API-ключ bnrouter. Адрес сайта отличается от адреса API.

curl

curl https://console.bnrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://console.bnrouter.com/v1",
)

resp = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Replace YOUR_API_KEY and YOUR_MODEL_ID with values from the console. Do not assume a model id that is not listed there.

Pricing

See current price in console.

Questions

What is MiniMax H3 Max?

MiniMax’s docs describe MiniMax H3 Max as a fast video generation model built on MiniMax H3, supporting text-to-video, image-to-video, and reference generation at 480P or 768P and 5–15 seconds.

Is MiniMax H3 Max the same as MiniMax M3.1 Flash?

No. H3 Max is a video generation model. M3.1 Flash is a separate chat / agent model family. bnrouter keeps distinct landing pages for each.

How do I call MiniMax H3 Max through bnrouter?

Create a key in the console and confirm the model id there or via GET /v1/models. Chat completions may be a poor fit — see the Image & video API docs. The plaza may still show coming soon.

What model id should I send?

Use the identifier listed for this model in the console or returned by GET /v1/models. A gateway model id is not configured in this repository. Do not treat MiniMax-H3-Max or fal route names as a bnrouter id.

How much does the MiniMax H3 Max API cost on bnrouter?