minimax-h3-rh-enhancedMiniMax H3 RH Enhanced is an enhanced build of the open-source MiniMax H3 video model. One model id covers three modes, picked automatically from what you send: a prompt alone is text-to-video; a first frame and/or last frame is image-to-video; reference images, reference videos or reference-video audio switch it to multi-reference generation (up to 9 images, 3 videos and 2 reference-video audio tracks). In every mode you can add a driving audio track for lip sync, and in image-to-video and multi-reference up to 3 voice references; audio_mode controls the soundtrack — native (default), lock_source to keep your audio untouched (music videos), remix_source or reference_only. Three resolutions — 480P, 768P and 1080P — in eight aspect ratios (1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9), any length from 4 to 15 seconds. You pay for the seconds you request: 480P $0.05/s, 768P $0.07/s, 1080P $0.10/s, so a 768P 10-second clip is $0.70 and a 1080P 15-second clip is $1.50; reference images, videos and audio cost nothing extra. In our own tests on 2026-10-10 a 480P 4-second clip came back with an audio track in 46-62 seconds (864x480 at 16:9, 24 fps), a 1080P clip in about 3.5 minutes (1920x1088), and a request carrying a reference video in about 6 minutes. Only successful generations are charged; failures and safety-review rejections are refunded.
Speech or a song the character moves to. MP3 / WAV, ≤15MB. Free.
The model creates the soundtrack
Generated video will appear here
Provide URLs and click Generate
Text-to-video, first/last-frame image-to-video and multi-reference generation share one model id; the mode is picked from the inputs you send
Up to 9 reference images, 3 reference videos and 2 reference-video audio tracks to carry characters, products, motion and rhythm into one clip
Pass a driving audio track and the speaker moves to it; audio_mode lock_source keeps your track untouched for music videos, and up to 3 voice references steer the voice
480P, 768P or 1080P in eight aspect ratios from 21:9 to 9:16, any length from 4 to 15 seconds
480P $0.05/s, 768P $0.07/s, 1080P $0.10/s for the seconds you request — references cost nothing extra
Failed generations and safety-review rejections are refunded automatically
MiniMax H3 RH Enhanced is a Video Generation API provided by MiniMax. MiniMax H3 RH Enhanced is an enhanced build of the open-source MiniMax H3 video model. One model id covers three modes, picked automatically from what you send: a prompt alone is text-to-video; a first frame and/or last frame is image-to-video; reference images, reference videos or reference-video audio switch it to multi-reference generation (up to 9 images, 3 videos and 2 reference-video audio tracks). In every mode you can add a driving audio track for lip sync, and in image-to-video and multi-reference up to 3 voice references; audio_mode controls the soundtrack — native (default), lock_source to keep your audio untouched (music videos), remix_source or reference_only. Three resolutions — 480P, 768P and 1080P — in eight aspect ratios (1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9), any length from 4 to 15 seconds. You pay for the seconds you request: 480P $0.05/s, 768P $0.07/s, 1080P $0.10/s, so a 768P 10-second clip is $0.70 and a 1080P 15-second clip is $1.50; reference images, videos and audio cost nothing extra. In our own tests on 2026-10-10 a 480P 4-second clip came back with an audio track in 46-62 seconds (864x480 at 16:9, 24 fps), a 1080P clip in about 3.5 minutes (1920x1088), and a request carrying a reference video in about 6 minutes. Only successful generations are charged; failures and safety-review rejections are refunded. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: 480P · per second: $0.05, 480P · 5s: $0.25, 480P · 10s: $0.5, 480P · 15s: $0.75, 768P · per second: $0.07, 768P · 5s: $0.35, 768P · 10s: $0.7, 768P · 15s: $1.05, 1080P · per second: $0.1, 1080P · 5s: $0.5, 1080P · 10s: $1, 1080P · 15s: $1.5, Reference images / videos / audio: $0.
Quickly generate brand promotion videos for ad campaigns and social media marketing.
Create compelling short-form video content for platforms like TikTok, Instagram, and YouTube.
Generate product feature demonstrations and tutorials to improve user conversion.
Produce course explanations, knowledge explainers, and training videos at an affordable price.
MiniMax H3 RH Enhanced is available through APIMODELS at: 480P · per second: $0.05, 480P · 5s: $0.25, 480P · 10s: $0.5, 480P · 15s: $0.75, 768P · per second: $0.07, 768P · 5s: $0.35, 768P · 10s: $0.7, 768P · 15s: $1.05, 1080P · per second: $0.1, 1080P · 5s: $0.5, 1080P · 10s: $1, 1080P · 15s: $1.5, Reference images / videos / audio: $0. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same MiniMax H3 RH Enhanced model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
On APIMODELS, MiniMax H3 RH Enhanced runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Text-to-Video, First / Last Frame, Multi-Reference · 9 Images · 3 Videos, Driving Audio · Lip Sync, Audio Modes, 480P / 768P / 1080P, 4-15s, From $0.05/s, and you can weigh it on price and capability against other Video Generation models, then switch by changing a single model-name string — no new account or integration. Browse every Video Generation option with live pricing at apimodels.app/models.
MiniMax H3 RH Enhanced supports: Text-to-Video, First / Last Frame, Multi-Reference · 9 Images · 3 Videos, Driving Audio · Lip Sync, Audio Modes, 480P / 768P / 1080P, 4-15s, From $0.05/s. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes MiniMax H3 RH Enhanced through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.
Prompts shared by their authors — copy and adapt them. Each one credits its author and links back to the original post.
Neon Tokyo Music Video (native stereo audio)
Music video. The soundtrack is a high-energy city-pop / synthwave track with a driving bassline, punchy live drums and a bright analog synth hook, playing continuously from the first frame. Neon-lit Tokyo backstreet at night in the rain. A young female singer in an oversized translucent raincoat performs straight to camera under a red izakaya lantern, singing the hook in sync with the music. Fast cuts landing on the beat: wide shot down the alley with neon reflected in puddles; tight close-up of her face with magenta rim light and rain on her cheek; low-angle push as she walks toward camera when the bass drops; quick insert of rain hitting a buzzing neon sign; back to a wide performance shot as the hook repeats. Anamorphic lens flares, shallow depth of field, 35mm film grain, teal and magenta palette, cinematic colour grade. No on-screen text.
by APIMODELS
Living Wallpaper: Aurora Lake (locked camera)
Locked-off static camera. No zoom, no pan, no dolly, no parallax. Only ambient atmosphere moves: the aurora ribbons drift and undulate slowly across the night sky, thin low mist creeps gently across the lake, the water surface breathes with extremely subtle ripples while keeping the mirror reflection intact, faint stars shimmer. Calm, continuous, seamless ambient loop. Nothing enters or leaves the frame, no new objects, no people, no text.
by APIMODELS
Condor Heroes characters teach English word dream
神雕侠侣主角趣味讲单词 dream 教程
by @nicekate8888
We curate copy-ready prompt libraries — every entry shows its full text and a sample result, ready to adapt.