Create highly realistic videos. Toggle Pro for higher quality. Supports text-to-video and image-to-video (image becomes the first frame). Choose orientation and seconds; size must match orientation.
Added Oct 6, 2025
Approx. Price
$0.400 per video
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
N/A
Duration
Default
8
Options (3)
4 seconds, 8 seconds, 12 seconds
Video length in seconds
Orientation
Default
landscape
Options (2)
Landscape, Portrait
Landscape or Portrait; affects the size sent to Sora
Pro Mode
Default
No
Higher fidelity (different per-second pricing)
Resolution Tier
Default
720p
Options (2)
720p (1280x720 or 720x1280), 1792x1024 (or 1024x1792, Pro only)
Pricing tier (per second)
Benchmarks
Benchmarks
Human preference benchmarks sourced from LMArena.
Text to Video
#7 / 44
Arena Score
1366.1
Votes
45,731
Confidence Interval
1358.8 - 1373.4
Published 2026-08-11 · Matched as sora-2-pro
LMArena DatasetExamples
Loading examples…
Related video models
Compare Sora 2 with similar models from the same provider or model family.
LTX-2.5 Fast
lightricks/ltx-2.5/fastSpeed-optimized audiovisual generation from text, an image, or a 2-20 second audio clip. Creates synchronized video and audio in one pass, with output up to 4K and optional start/end-frame control.
LTX-2.5 Pro
lightricks/ltx-2.5/proHigh-fidelity audiovisual generation from text, an image, or a 2-20 second audio clip. Creates polished synchronized video and audio in one pass, with 720p/1080p output and optional start/end-frame control.
Wan 3.0 Image-to-Video
alibaba/wan-3.0/image-to-videoAnimate a first-frame image into a cinematic video with optional last-frame guidance, synchronized audio, deep-thinking controls, and 2–30 second output.
Wan 3.0 Reference-to-Video
alibaba/wan-3.0/reference-to-videoReference-guided video generation using images, videos, and audio for subject consistency, motion, timing, and scene continuity, with 2–30 second output.
Wan 3.0 Text-to-Video
alibaba/wan-3.0/text-to-videoCinematic text-to-video generation with synchronized audio, deep-thinking prompt interpretation, 2–30 second duration, and 480p, 720p, or 1080p output.
Wan 2.2 Animate 2
wan-22-animate-2Next-generation character motion transfer with strong identity preservation and prompt-controlled backgrounds. Requires a reference image and driver video; supports 480p/720p up to 120s.