Sora 2 is OpenAI's text-to-video and image-to-video model
One wallet. Every model.
One model. Every resolution. One credit balance.
Examples
Every clip below is one pass. No post-production.
Branded can. Headline that reads.
Image-to-video (12s), Sora 2 by OpenAI. A matte-black drink can on a warm cream studio backdrop, gold infinity mark on the front. A slow gentle push-in while the headline "AI AD CREATIVE" and the "Coinis" wordmark stay crisp and legible.
Sneaker. Orange powder burst.
Image-to-video (12s), Sora 2 by OpenAI. A white-and-orange running sneaker erupts through an orange and gold powder burst in slow motion, then holds as hero as the powder settles.
Perfume. Gold powder burst.
Image-to-video (12s), Sora 2 by OpenAI. A frosted perfume bottle erupts through a gold and amber powder burst in slow motion, then the bottle holds as hero as the powder settles.
Headphones. Blue powder burst.
Image-to-video (12s), Sora 2 by OpenAI. Navy-and-gold headphones erupt through a deep blue and gold powder burst in slow motion, then hold as hero as the powder settles.
Watch. Gold powder burst.
Image-to-video (12s), Sora 2 by OpenAI. A luxury watch erupts through a gold and bronze powder burst in slow motion, the case gleaming, then holds as hero as the powder settles.
Coffee. Beans and powder burst.
Image-to-video (12s), Sora 2 by OpenAI. A kraft coffee bag erupts through a brown and gold coffee-powder burst with flying beans in slow motion, then holds as hero as the cloud settles.
Skincare. Pink powder burst.
Image-to-video (12s), Sora 2 by OpenAI. A ceramic skincare jar erupts through a soft pink and gold powder burst in slow motion, then holds as hero as the powder settles.
Capabilities
01
Text-to-video generation from natural language prompts
02
Image-to-video conditioning: upload a JPEG, PNG, or WebP as the first frame
03
Video extension: continue a completed clip to build longer scenes
04
Sora 2: 720p portrait (720x1280) and landscape (1280x720)
05
Sora 2 Pro: 720p, 1024p portrait (1024x1792) and landscape (1792x1024)
06
Up to 20 seconds per generation (4, 8, 12, and 16-second presets supported)
07
Synchronized speech, sound effects, and ambient soundscapes
08
Non-human character upload (mascots, animals, objects) for multi-clip consistency
09
World-state persistence: objects maintain spatial relationships across cuts
10
Asynchronous Videos API with job ID, status polling (queued, in_progress, completed, failed), and webhook support
11
MP4 output plus downloadable thumbnail and spritesheet
12
Signed download URLs valid for 1 hour after generation
13
Batch API submission available for large offline render queues at reduced cost
14
C2PA metadata and SynthID-style watermarking on all generated outputs
No code. No API. Describe what you want. Get ad-ready output.
Paste a product link or a short brief. Coinis pulls your brand.
Choose the model for the look you want. Switch anytime.
Generate. Launch to Meta. Track results in one place.
One wallet. Every model. No accounts to juggle.
One wallet across every model. No API accounts to juggle.
No credit card.
1 credit = $0.01 pay-as-you-go. Less on a plan.
Video, image, audio, and LLM in one place.
Same brief. Many cuts. No accounts to juggle.
Download it. Run it in any campaign.
Prompt to platform-native clip in minutes.
One generation, every aspect ratio.
Authentic selfie-style ads, on brand.
Renders in seconds. Set a seed. Get the same frame back.
Outputs are yours. Sell them.
Safe for paid ads.
Your prompts are never used for training.
Start free
Start free. 150 credits a week. No card.
Generate on CoinisNo credit card.
Pricing and capabilities verified 2026-06-04. Read the docs .