Veo 3.1 Fast
Google's video model with sound. Fast and affordable, great for Reels and ads.
With soundUp to 8 sStart from an image
from 84.3M credits
per video
1–2 min
4/6/8 s · 1080p
Classai Router · Video AI
Type a scene.
Get a film with sound.
Veo, Seedance, Wan, HappyHorse, MiniMax and Oxygen in one studio: a sentence — or a still image — becomes a 3–30-second clip with camera motion, voices and ambient sound. Vertical for Reels, wide for YouTube. Paid per video, only when it's done.
- video models
- 12
- video models
- clip length
- 3–30 s
- clip length
- max resolution
- 1080p
- max resolution
- typical wait
- 1–2 min
- typical wait
From 33.3M credits per video. Failed videos are free.
Veo 3.1 Fast · 8 s
Seedance 2.0 Fast · 5 s
Video prompt:
Describe a scene…
Image & video models from Google OpenAI
Microsoft ByteDance Black Forest Labs
Alibaba
MiniMax AZ8
Microsoft ByteDance Black Forest Labs Alibaba MiniMax AZ8The models
Every top video model. One studio, one price list.
Pick per job: the Fast and Mini tiers for Reels, ads and drafts, the flagships for cinematic shots and realistic people. All start from text or from a still image, and most come with sound.
Veo 3.1
Veo's highest quality: cinematic motion, realistic people and sound.
Best qualityWith soundStart from an image
from 337M credits
per video
1–3 min
4/6/8 s · 1080p
Seedance 2.5
ByteDance
ByteDance's newest video model: up to 30 seconds with sound, cinematic camera work.
NewUp to 30 sWith sound
from 87.7M credits
per video
2–6 min
4–30 s · 1080p
Seedance 2.0
ByteDance
Seedance 2.0: smooth motion and consistent characters, with sound, up to 1080p.
With soundUp to 15 s1080p
from 60M credits
per video
2–3 min
4–15 s · 1080p
Seedance 2.0 Fast
ByteDance
The quicker Seedance 2.0 for drafts and social clips.
FastWith sound
from 38M credits
per video
1–3 min
4–15 s · 720p
Seedance 2.0 Mini
ByteDance
The cheapest Seedance with sound: great value for many short clips.
CheapWith sound
from 33.3M credits
per video
1–2 min
4–15 s · 720p
Wan 3.0
Alibaba
Alibaba's Wan 3.0: native soundtrack, up to 30 seconds, the lowest price per second.
Cheapest per secondUp to 30 sWith sound
from 33.3M credits
per video
2–3 min
3–30 s · 1080p
Wan 3.0 Prime
Alibaba
Wan 3.0 on priority hardware: same model, faster results.
FasterWith sound
from 38M credits
per video
1–2 min
3–30 s · 1080p
Wan 2.7
Alibaba
Wan 2.7 text- and image-to-video at 720p or 1080p, with sound.
With soundStart from an image
from 50.7M credits
per video
1–3 min
3–15 s · 1080p
HappyHorse 1.1
Alibaba
Alibaba's HappyHorse: lifelike motion that keeps the subject steady.
Stable subjectsStart from an image
from 62.7M credits
per video
1–3 min
3–15 s · 1080p
MiniMax H3
MiniMax
MiniMax's H3 (Hailuo family): stereo sound always on, up to 15 s. Slow but cheap.
With soundUp to 15 sCheap
from 33.3M credits
per video
3–10 min
4–15 s · 768p
Oxygen 1.0
AZ8
Budget video model with a native soundtrack, same price at 480p and 768p.
CheapestWith soundUp to 15 s
from 33.3M credits
per video
1–3 min
4–15 s · 768p
Made with Veo, Seedance, Oxygen, MiniMax and Wan
Press the speaker. These clips came with their sound.
Unedited clips straight from the models — picture, camera motion and audio generated together from one prompt.
Veo 3.1 Fast · 8 s
Veo 3.1 Fast · “Cinematic drone shot rising slowly over Bali rice terraces at sunrise, mist drifting in the valleys, birds flying across the frame, calm ambient nature sounds”
Veo 3.1 Fast · 8 s
Veo 3.1 Fast · “The camera slowly pushes into the warung, light rain keeps falling, a man takes a sip of coffee and smiles, soft rain and distant traffic sounds”
MiniMax H3 · 6 s
MiniMax H3 · “A Balinese legong dancer performs in a temple courtyard at golden hour, expressive eyes and hand movements, gold costume shimmering, gamelan music, slow cinematic dolly”
Wan 3.0 · 5 s
Wan 3.0 · “Children fly colorful kites on a wide Indonesian beach at sunset, the camera tracks along the sand, waves rolling in, wind and laughter sounds”
Seedance 2.0 Fast · 5 s
Seedance 2.0 Fast · “Slow orbit around the iced palm-sugar coffee, ice cubes shift and condensation drips, warm morning light, upbeat acoustic guitar”
Seedance 2.0 Fast · 5 s
Seedance 2.0 Fast · “Close-up of sate being grilled over glowing charcoal at a night market, smoke and sparks rising, the vendor fans the coals, sizzling sounds and crowd ambience”
Oxygen 1.0 · 6 s
Oxygen 1.0 · “A woman with a clear umbrella walks through a rainy Jakarta street at night, neon reflections in puddles, cars passing with headlights, rain and traffic sounds, cinematic”
For AI agents & developers
Built for AI agents & developers.
Let your agent make videos through MCP, call the OpenAI-compatible API from your code, or hand your coding agent one prompt that wires it into your app.
- OpenAI-compatible
- One key for chat, voice, image, video
- Pay only for what comes out
- llms.txt + OpenAPI
- MCP server
Connect once and your agent can make videos itself — in Claude Code, Claude Desktop, Cursor, opencode or any MCP client. Streamable HTTP, authenticated with your sk_live_ key.
Tools
start_videoget_videolist_media_modelsgenerate_imageedit_imagespeakServer URL
https://router.classai.id/mcpclaude mcp add --transport http classai https://router.classai.id/mcp \
--header "Authorization: Bearer sk_live_…"How it works
Three steps. No subscription.
1
Describe the scene
Write the shot like a director: subject, camera move, mood and what we should hear. Or upload a still image and let it come alive.
2
Pick length and format
3–30 seconds, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, up to 1080p — each model shows its own options. The price shows before you press Generate; the clip renders in the background.
3
Pay for what comes out
Credits are taken only for videos that are delivered. Blocked prompts and failed generations cost nothing.
Two formats
Every shape your channel needs.
Pick the aspect ratio before you generate — the model composes for it, nothing gets cropped afterwards.
9:16 — Reels, TikTok, Stories, Shorts
Seedance 2.0 Fast · 5 s
Start from a picture
Make the still first, then bring it to life.
Real outputs from our image models — any of them can be the first frame of a video. Explore Image AI
Pricing
Pay per video, from 33.3M credits.
No subscription and no monthly minimum. The price per video is shown before you generate.
Failed = freeBlocked prompts, errors and timeouts are never charged.
Valid 30 daysEach credit pack lasts 30 days and works on every model — chat, voice, image and video.
Credits onlyToken packages (for coding models) don't cover images or videos — use credits.
The Pro pack alone makes about 75 images on GPT Image 2.5 Flare or 7 videos on Seedance 2.0 Mini. Images from 3.3M credits, videos from 33.3M credits.
Credit packs — the same credits work for every model
Pro
250M credits
$0.02 / 1M credits
To try every model, or for light use.
- All active models, all API keys
- Valid 30 days from payment
One-time payment
$4.99
Max
Save 25%500M credits
$0.015 / 1M credits
Regular daily use, cheaper per credit.
- All active models, all API keys
- Valid 30 days from payment
One-time payment
$7.49
Ultra
Best value1 billion credits
+ Bonus 100M credits
$0.012 / 1M credits · save 40% vs Pro
The best value per credit for heavy use.
- All active models, all API keys
- Valid 30 days from payment
One-time payment
$11.99
FAQ
Questions, answered.
Something else? Contact our support.
No impersonation, no deepfakes. Realistic people? Say it's AI.
Can I use the videos commercially?+
Yes — ads, social posts, product pages, thumbnails, courses and client work. When a picture or clip shows realistic people, tell viewers it's AI-generated.
What isn't allowed?+
Impersonating real people, deepfakes of public figures or anyone without their consent, sexual content involving minors, and content made to deceive (fake news, fake documents). The safety filter blocks prompts like these, and accounts that keep trying are closed.
What if a generation fails or the safety filter blocks it?+
You're not charged. Credits are taken only for videos that are actually delivered — a blocked prompt, a timeout or an upstream error costs nothing.
What resolution can I get?+
Images: Nano Banana Pro up to 4K, Nano Banana 2.1 up to 4K, Nano Banana 2 up to 4K, Nano Banana 2 Lite up to 1K, Nano Banana up to 1K, GPT Image 2.5 Flare up to 2K, GPT Image 2.5 Sunburst up to 2K, GPT Image 2 up to 2K, GPT Image 1.5 up to 1K, ChatGPT Image up to 1K, GPT Image 1 up to 1K, GPT Image 1 Mini up to 1K, GPT Image 2.5 Lite up to 4K, MAI-Image 2.6 up to 1K, MAI-Image 2.6 Flash up to 1K, Seedream 5.0 Pro up to 2K, Seedream 5.0 up to 3K, Seedream 5.0 Flash up to 2K, Seedream 4.5 up to 4K, Seedream 4.0 up to 4K, FLUX.2 Max up to 2K, FLUX.2 Pro up to 2K, FLUX.2 Flex up to 2K, FLUX.2 Klein up to 2K, FLUX.1 Dev up to 1K, FLUX Kontext Max up to 1K, FLUX Kontext Pro up to 1K. Videos: up to 1080p, 3–30 seconds, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 — each model shows its own options in the studio.
How long does it take?+
Images take 2–6 s on FLUX.2 Klein and 20–240 s on GPT Image 2. Videos usually take 1–10 minutes; they render in the background and wait in your Studio history.
Do I need a separate API key?+
No. The same sk_live_ key and base URL you use for AI models and voice work here. GET /v1/media/models lists every image and video model with its price. Links returned by the API last 24 hours — download what you want to keep.
Do token packages cover images and videos?+
No — images and videos are paid from credits only (token packages are for coding models). Credits are valid 30 days per purchase and also work for every AI model and voice.
Your next clip is one sentence away.
Type a scene, pick a format, press Generate. Your clip — with sound — in a couple of minutes.
Create a free account