Dreamina Seedance 2.5
Video generation
dreamina-seedance-2-5-260628
$10.70 per 1m tokens 480p 720p
Dreamina Seedance 2.0
ByteDance Seed’s early-2026 audio-video model, predecessor of Seedance 2.5 and still sold on BytePlus ModelArk in standard, Fast and Mini tiers.
Model iddreamina-seedance-2-0-260128
Price$7 per 1m tokens 480p 720p
Checked25 October 2026
Where it stands
14newer video generation models since its release
- FLUX 3 Max19 Oct 2026
- Kling 4.0 (and 4.0 Flash)15 Oct 2026
- Tavus Griffin (Human Interaction Model)1 Oct 2026
- HeyGen Video 130 Sep 2026
- Utopai X30 Sep 2026
The 5 newest are listed. All video generation models
- After it from ByteDance Seed
- Dreamina Seedance 2.531 Jul 2026
- Weights
- Closed weights; access is hosted only.
How to call it
6 ways to use Dreamina Seedance 2.0, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| BytePlus ModelArk | dreamina-seedance-2-0-260128 |
https://ark.ap-southeast.bytepluses.com/api/v3/ |
docs.byteplus.com |
| BytePlus ModelArk (Fast) | dreamina-seedance-2-0-fast-260128 |
||
| BytePlus ModelArk (Mini) | dreamina-seedance-2-0-mini-260615 |
||
| OpenRouter | bytedance/seedance-2.0 |
||
| OpenRouter (Fast) | bytedance/seedance-2.0-fast |
||
| Web app | seed.bytedance.com |
Pricing
| Per 1m tokens 480p 720p | $7 |
|---|---|
| Per 1m tokens 1080p | $7.70 |
| Per 1m tokens 4k | $4 |
| Per 1m tokens with video input 480p 720p | $4.30 |
| Per 1m tokens with video input 1080p | $4.70 |
As published: “USD per 1M video tokens on BytePlus ModelArk (online inference). BytePlus examples, 5 s 16:9 without video input: 480p 0.35 (0.07/s), 720p 0.76 (0.15/s), 1080p 1.87 (0.37/s), 4K 3.89 (0.78/s). Fast variant 5.6/1M (480p/720p only), Mini 3.5/1M”.
Source: docs.byteplus.com, checked 25 October 2026.
Specs
- Input
- Text, images, video and audio
- Output
- Video and audio
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- February 2026
- Status
- Current
- Type
- Video generation
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Unified audio-video joint generation
Generates picture and sound together from text, image, audio and video inputs in one multimodal architecture.
Multimodal reference and editing
Open platform accepts up to 9 images, 3 video clips and 3 audio clips as references; 4-15 s outputs, native 480p/720p (BytePlus also bills 1080p and 4K).
Technical report
Found after launch
Seed published a technical report (arXiv 2604.14148, 2026-04-15) with self-reported SeedVideoBench-2.0 results.
Notes
Artificial Analysis text-to-video leaderboard (read 2026-10-25): #9, Elo 1136; AA lists release Mar 2026 and price 22.45 USD per minute of 1080p (matches BytePlus 0.37/s). Still listed as an active (not retiring) model on BytePlus pricing as of 2026-10-25, alongside Fast and Mini (Mini id dated 260615). Superseded as flagship by Seedance 2.5 (2026-07-31). The OpenRouter Mini id is bytedance/seedance-2.0-mini. No timeline entry for its launch.
Artificial Analysis text-to-video (with audio) leaderboard, read 2026-10-25: rank 9, Elo 1136 (https://artificialanalysis.ai/video/leaderboard/text-to-video).
Sources: https://seed.bytedance.com/en/seedance2_0 · https://seed.bytedance.com/en/public_papers/seedance-2-0-advancing-video-generation-for-world-complexity · https://docs.byteplus.com/en/docs/modelark/model-pricing
Not yet checked against an official source: Seed says it was ‘officially released in China in early February 2026’ (third parties give 2026-02-12; exact day not verified on a ByteDance page, so month precision).