SeedreamImage
ByteDance Seedream — fast, high-fidelity text-to-image.
22.3sp50100%up1 rail$0.04/image
ByteDance Seedance — reference-driven text- and image-to-video.
Collecting — charts appear after two days.
# 1 · start the render
curl https://www.ninjachat.ai/api/v1/videos \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "seedance-2", "prompt": "a paper boat drifting down a neon rain stream", "duration": 8, "aspect_ratio": "16:9" }'
# 2 · poll until it is ready
curl "https://www.ninjachat.ai/api/v1/videos/JOB_ID" \
-H "Authorization: Bearer $NINJACHAT_API_KEY"ByteDance Seedance — reference-driven text- and image-to-video.
Seedance 2.0 costs $0.35/sec.
Seedance 2.0 accepts text and image and returns video.
POST /api/v1/videos with `"model": "seedance-2"`.
Seedream.
Google Veo — cinematic text-to-video with native audio.