Seedance 2.0
seedance-2.0
The frontier video model. Text-to-video and image-to-video up to 4K with native audio — cinematic motion and strong prompt-following.
720p · 1080p · 4Ktext + image → videonative audioup to 15s
One OpenAI-compatible API, one wallet, one dashboard. New models are added continuously —
list them anytime with GET /v1/models.
One model family, three tiers. Start with flagship 4K quality, then trade resolution for speed and cost as your volume grows.
The frontier video model. Text-to-video and image-to-video up to 4K with native audio — cinematic motion and strong prompt-following.
The same core model tuned for speed — ideal for iteration, previews, and high-volume pipelines.
The most affordable way to prototype cinematic AI video at scale.
Video billed per output second — 720p $0.15 · 1080p $0.25 · 4K $0.60. A 4-second 720p clip starts at $0.60.
Long-context conversational models over the same OpenAI-compatible endpoint — swap the base URL and keep your SDK.
256K-context conversational models over the same OpenAI-compatible endpoint. Token-by-token streaming — point your SDK’s base_url at us and change nothing else.
On the roadmap — text-to-image and editing, served the same drop-in way.
Seedream 5.0 / 4.5 text-to-image and image editing via /v1/images/generations.
Free trial credits on signup — no card required to start. Read the docs or grab a key and ship today.