All models / Video / FastH3-Omni (real-time video + audio)

FastH3-Omni (real-time video + audio)

Name: FastH3-Omni (real-time video + audio)
Brand: MiniMax
Price: 0.0128 USD
Availability: InStock

model id: reactor/fast-h3-omni

Real-time · Text in → Video out realtime-video-generation

Hosts

Host	Price	Max session
Reactor	$0.0128 / s	900 s

0% additional markup beyond our 2.5% platform fee.

No live Playground for this model yet

This model streams from the host’s own SDK, and the browser half of that is yours to build. Switch to the API tab above for the session call, or see Live video & world models for the host’s browser example.

About

FastH3-Omni: queue 5-15 s clips driven by text, reference images (up to 3 in real time), audio references, first/last-frame keyframes or a continuation of an earlier clip, with synchronized audio, and play them on demand. Real-time speed holds with up to 3 reference images; with 4-9 a clip takes longer to build than to play (billed per session second).

Price

$0.0128 / second

per second the session is live — about $46.12 per hour

Includes the VideoRouter platform fee of 2.5% of provider cost.

Specs

KindReal-time video generation

CreatorMiniMax

InputText

OutputLive video stream

Resolution768p

Max session900 s

Default session120 s

How it works

Your server calls POST /v1/live-video/sessions with this model id. We check your key and credits, hold the cost of the session, and return a short-lived credential for the host.
Your browser or app streams from the host directly with that credential — the video never passes through our servers and the host API key never reaches the browser.
Your server sends a heartbeat while it runs and ends the session when the user leaves. You pay per second the session was live, up to 900 s per session.

Full reference, limits and errors: Live video & world models.

from videorouter_live import LiveVideo
lv = LiveVideo(api_key="llmr_sk_live_...")   # or set VIDEOROUTER_API_KEY

# On YOUR server: open a session, hand `connect` to the browser, settle on exit.
with lv.session(
    "reactor/fast-h3-omni",
    max_duration_seconds=60,
) as s:
    send_to_browser(s.connect)      # returned once; short-lived credential for the host
    wait_for_user_to_finish()
print(s.status, s.billed_seconds, s.cost_usd)

import { LiveVideo } from "videorouter-live";
const lv = new LiveVideo({ apiKey: process.env.VIDEOROUTER_API_KEY });

// On YOUR server: open a session, hand `connect` to the browser, settle in a finally.
const session = await lv.withSession(
  {
    model: "reactor/fast-h3-omni",
    maxDurationSeconds: 60,
  },
  async (session) => {
    await sendToBrowser(session.connect);   // returned once
    await waitForUserToFinish();
    return session;
  },
);
console.log(session.status, session.billedSeconds, session.costUsd);

curl https://videorouter.sh/api/v1/live-video/sessions \
  -H "Authorization: Bearer llmr_sk_live_..." \
  -H "Content-Type: application/json" \
  -d '{"model": "reactor/fast-h3-omni", "max_duration_seconds": 60}'

# keep it alive while the user streams, then settle:
curl -X POST https://videorouter.sh/api/v1/live-video/sessions/$SESSION_ID/heartbeat -H "Authorization: Bearer llmr_sk_live_..."
curl -X POST https://videorouter.sh/api/v1/live-video/sessions/$SESSION_ID/end -H "Authorization: Bearer llmr_sk_live_..."