Dreamina Seedance 2.0 (International)

Models / Tiers

Per-second billing (4-15s), charged only on success and refunded on failure. Native resolution — no upscaling.

Price cut on 8 August 2026: Mini down ~56%, Fast down ~24%, standard tier unchanged. A job carrying a reference video bills on a different basis — a lower per-second rate, but charged on (source seconds + output seconds), so editing or continuing a clip into an output of the same length is not more affordable than generating it outright. Mini $0.0138 / $0.030, Fast $0.0378 / $0.0812 (480p / 720p).

Video Generation

# Text-to-video (model: dreamina-seedance-2-0 / -fast / -mini)
curl -X POST https://api.apimodels.app/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dreamina-seedance-2-0-fast",
    "prompt": "a hummingbird hovering near a bright flower, slow motion",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5
  }'

# Real people: this line does NOT accept a real, identifiable person in reference
# images or videos (upstream policy, checked 2026-09-29) — the task fails at creation
# and is not billed. For real-person video use our seedance-2.0 / seedance-2.0-mini
# models (same key, same endpoint), where a photo URL is accepted: see /docs/seedance-2-0-official.

Reference assets are cited POSITIONALLY in the prompt: the first entry of reference_image_urls is 图片1 / @image1, the second is 图片2, and so on; reference_video_urls follows the same pattern as 视频1 / @video1. The number follows the order of the array you send and has nothing to do with filenames — to make one image the hero, either put it first or refer to it by the position it actually occupies. Telling each asset what to supply and what NOT to supply beats sending more of them.

Real people

Since 29 September 2026 this international line does not accept real people in reference media: a reference image or video showing a real, identifiable person is rejected at task creation with "a reference image or video appears to show a real, identifiable person"; nothing is billed, and retrying with the same media fails again. There is no asset-library (asset://) path on this line either.

For real-person video use our seedance-2.0 / seedance-2.0-mini models (same site, same key): pass the photo as an https URL (if the upstream rejects it, the system registers it as an asset and retries automatically). Same endpoint and fields — only the model changes. Seedance 2.0 docs

Notes

• Real people: not accepted on this line; for real-person video use our seedance-2.0 / seedance-2.0-mini models.
• First-frame and reference modes are mutually exclusive: when first_frame_url is present, reference_image_urls is ignored.
• Async: create returns a taskId; poll GET /v1/video/generations?task_id= until completed. Result files are kept 30 days — download or re-host promptly.

Try it in the Playground