Minimax Video-01 is a text-to-video model offering high compression, strong text responsiveness, cinematic styles, and native HD output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.5per run·~20 / $10
ExamplesView all
A futuristic spacecraft glides silently above the rings of Saturn. Inside, a lone astronaut gazes out the window. The scene alternates between wide shots of the ship and intimate interior shots bathed in control panel glow.
A tender moment between a mother and her child in a cozy living room, warm natural sunlight pouring through the window, soft focus on their smiling faces, mother gently hugging toddler, casual home clothing with gentle pastel colors, background filled with books and plants, slow gentle camera tilt from face to hands, warm and intimate mood, cinematic soft lighting, high resolution video capture
A cyberpunk male character with neon blue hair and futuristic glasses, half body shot, glowing cityscape background, vibrant neon colors, dynamic pose, sharp details, sci-fi style, medium lighting, high contrast, intense gaze
A stylish urban toy figure with oversized head and glossy plastic texture, dressed in streetwear with hoodies and sneakers, bold exaggerated facial features and bright neon eyes, dynamic poses with smooth camera rotations, graffiti background with vivid colors and stickers, high-gloss reflective surfaces, vibrant saturated color grading, high-detail 3D animated video with smooth motion
A young anime boy with messy brown hair and bright green eyes, wearing a leather jacket and backpack, standing in a mystical forest with oversized mushrooms, soft cel shading with bold outlines, expressive emotions ranging from curiosity to excitement, slow tracking camera following his footsteps, warm natural colors mixed with fantasy hues, smooth animated gestures, cinematic style
A cute claymation-style little girl with big round eyes and chubby cheeks, textured clay surface with visible fingerprints, simple bright clothing with playful patterns, stop-motion style subtle jitter in movements, pastel color background with hand-crafted props like flowers and toys, slow zoom-in focusing on her cheerful smile, tactile and whimsical vibe, high-quality animated video
A tender moment of a father holding his toddler in a cozy living room, natural window light softly illuminating their faces, father’s gentle smile and child’s curious gaze, casual comfortable clothing, detailed skin textures and subtle ambient reflections, slow close-up camera focusing on their warm interaction, warm homely color tones, realistic and heartfelt cinematic video
A refined Victorian era young lady standing in a grand ballroom, detailed lace gown with delicate embroidery, elegant updo hairstyle with jeweled hairpin, soft candlelight flickering creating warm shadows, slow graceful camera dolly highlighting intricate dress textures and porcelain skin, muted pastel color palette, classical and romantic atmosphere, cinematic video quality
A pixel art style girl standing in a retro arcade, colorful pixel sprites and blinking neon lights, simple but expressive pixel face and hairstyle, wearing 90s casual outfit, pixel animation of blinking eyes and breathing, arcade machines in the background with pixelated animations, nostalgic 8-bit color palette, smooth pixel art video
A young woman casually walking down a busy city street on a sunny afternoon, natural sunlight casting soft shadows on her face, loose hair gently moving with the breeze, wearing a comfortable sweater and jeans, subtle natural makeup highlighting her features, candid smile and relaxed expression, realistic skin texture with fine details, slow tracking camera following her from the front, vibrant yet natural color grading, cinematic video quality
A glamorous 1940s Hollywood actress in black and white, soft lighting with strong shadows typical of film noir, classic hairstyle and elegant evening gown, slow zoom-in capturing subtle facial expressions and vintage makeup, smoky background with dramatic shadows, grainy film texture effect, nostalgic cinematic video capturing timeless elegancevideo
A fluffy golden retriever puppy happily running through a park covered with colorful autumn leaves, warm sunlight, playful mood.
A bold street-style girl posing confidently in front of a large colorful graffiti wall, vibrant spray paint textures and animated paint drips, edgy outfit with bright patterns, dynamic camera movement zooming and panning around her, neon color splashes mixed with urban gray concrete, youthful and rebellious energy, stylized cinematic video with strong contrast and saturation
A steampunk-inspired girl with goggles and brass gears on her leather outfit, standing on a rooftop overlooking a smoky industrial city, warm amber and sepia tones, intricate mechanical details animated on her costume, slow rotating camera emphasizing textures and metal reflections, soft glowing steam effects swirling around, vintage Victorian-meets-futuristic atmosphere, high-detail cinematic video
A pixel art style young hero standing in a pixelated fantasy village, blocky and colorful sprites, simple but expressive pixel eyes and facial features, wearing a blue tunic and brown boots, holding a sword, background with pixel trees, houses, and animated NPC villagers, smooth pixel movement with walking animation frames, retro 16-bit style colors and shading, nostalgic video game vibe with subtle scanlines effect
A gentle countryside girl standing in a blooming sunflower field under a clear blue sky, sunlight casting soft shadows, long flowing hair with flower crown, simple white linen dress fluttering in the breeze, smiling softly looking towards horizon, natural vibrant colors, slow dolly shot capturing the vast field and her silhouette, peaceful and warm atmosphere, cinematic high definition video
A dynamic anime-style girl warrior standing on a cliff at sunset, big sparkling eyes and vibrant hair flowing in the wind, wearing futuristic armor with glowing accents, dramatic pose with sword raised high, colorful sky blending oranges and purples, soft cel-shading and clean line art, smooth fluid animation emphasizing hair and cape movement, background with stylized clouds and distant mountains, vivid saturated colors, high-energy cinematic video
A dreamy fantasy girl with flowing pastel pink hair, glowing magical particles swirling around her, ethereal soft light filtering through a mystical forest, delicate lace dress shimmering with sparkles, gentle smile and wide expressive eyes, slow graceful movement as if floating, soft bokeh background with blurred flowers and glowing orbs, cinematic mood, subtle color shifts between pink and lavender, ultra high-definition video
A futuristic warrior standing atop a skyscraper, neon city lights glowing below, wind blowing dramatically, camera slowly zooming in, cinematic style, epic atmosphere, intense colors, 4K quality
A smiling child in a yellow shirt running along a sunny beach, holding a colorful kite soaring high in the sky, ocean waves sparkling.
Related Models
README
MiniMax Video-01 — minimax/video-01
MiniMax Video-01 is a text-to-video (T2V) model for generating short, coherent clips from a single prompt. It’s built for cinematic pacing, stable scene continuity, and prompt-faithful motion, making it a strong default for story beats, product shots, and concept trailers.
What it’s good at
- Text-to-Video (T2V): generate a complete clip from a prompt
- Cinematic language: responds well to shot descriptions and camera cues
- Coherent motion: maintains continuity across frames for simple-to-moderate action
- Fast iteration: great for rapid creative exploration and storyboard-style outputs
Inputs
- Prompt (required): describe subject, action, environment, lighting, camera, and style
- Image (optional, if supported in your deployment): provide a reference frame to steer the look
- Enable prompt expansion (optional): automatically expands/optimizes your prompt for better visual quality
Key parameters
-
enable_prompt_expansion:
-
On: better visual richness and fewer “under-specified” results
-
Off: tighter control, closer to your exact wording (often best for structured prompts)
Prompting tips
-
Use a “director brief” structure:
-
Subject: who/what is on screen
-
Action: what changes over time
-
Scene: where + time of day + lighting
-
Camera: framing + movement + transitions
-
Style: mood + medium + references (optional)
-
Prefer one clear main action per clip (then iterate).
-
If you need stronger motion, add pace and intent: slowly, rapidly, abrupt cut, smooth dolly-in, handheld shake.
Use cases
- Concept trailers & story beats: quick visual drafts for narrative sequences
- Marketing clips: product mood videos and brand-style visuals
- Social content: punchy short clips with strong camera direction
- Pre-visualization: test shots, lighting, and staging before production
Pricing
| Model | Price per video |
|---|---|
| minimax/video-01 | $0.50 |
Video 01 API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/video-01 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Video 01 below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/minimax/video-01" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"enable_prompt_expansion": true
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("minimax/video-01", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"enable_prompt_expansion": true
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"minimax/video-01",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"enable_prompt_expansion": true
}
)
print(output["outputs"][0]) # → URL of the generated outputVideo 01 API — Frequently asked questions
What is the Video 01 API?
Video 01 is a MiniMax model for video generation from images, exposed as a REST API on WaveSpeedAI. Minimax Video-01 is a text-to-video model offering high compression, strong text responsiveness, cinematic styles, and native HD output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Video 01 API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-video-01.
How much does Video 01 cost per run?
Video 01 starts at $0.50 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Video 01 accept?
Key inputs: `prompt`, `image`, `enable_prompt_expansion`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/minimax/minimax-video-01.
How long does Video 01 take to generate?
Average end-to-end generation time on WaveSpeedAI is around 173 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Video 01 outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (MiniMax). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.