Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / BYTEDANCE
Seedance 2.0
verified model reference.
ByteDance joint audio-video generation model for cinematic multi-shot clips with text, image, audio and video references, served through BytePlus ModelArk.
Not publishedcontext not published
Not publishedmax output
2026-10-12last verified
PRIMARY-SOURCE VERIFIED
Seedance 2.0 at a glance.
ByteDance does not publish a token context window for this service. Input modalities: text + image + audio + video. Output: video + audio. Pricing status: Official paid API.
MODEL IDdreamina-seedance-2-0-260128
CONTEXT WINDOWNot published
MAX OUTPUTNot published
KNOWLEDGE CUTOFFNot published
STANDARD INPUT$7.00per 1M metered service tokens (no video input, 480p/720p only)
STANDARD OUTPUT—per 1M metered service tokens (no video input, 480p/720p only)
CAPABILITY CONTRACT
Published model behavior.
text + image + audio + video
Input modalities come from the cited official model documentation.
video + audio
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
Official paid API.
$7.00 input per 1M metered service tokens (no video input, 480p/720p only).
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
What the source record does not assume.
01
BytePlus ModelArk native ID is dreamina-seedance-2-0-260128. This is distinct from Seedance 2.0 Fast or Mini; account activation, region and service availability must be checked in BytePlus.
02
The catalog's displayed reference Standard rate ($7.00 per 1M billed service tokens) applies ONLY to 480p/720p generation without video in the input. BytePlus also lists $4.30 with video input at 480p/720p; $4.70 with video input at 1080p and $7.70 without video input at 1080p.
03
Billing depends on resolution, model configuration and token consumption; this is NOT a per-generated-text-token rate or a guaranteed price per clip. The generic text cost calculator excludes Seedance.
04
ByteDance documents 4–15 second native audio/video generation, including references to up to 9 images, 3 video clips and 3 audio clips. Max output tokens/context window for a text LLM do not apply to video output.
EXPLORE
Keep the model in context.
OFFICIAL SOURCES
Verification links.
WHAT CHANGED
Seedance 2.0: what changed.
No post-baseline factual changes recorded for Seedance 2.0 since 2026-10-12.
VERIFIED BASELINE2026-10-12Current facts remain aligned with the SXF ledger.
VERIFIED CHANGE HISTORY
Seedance 2.0 verified history.
Seedance 2.0
Baseline verified: context not published · Not published max output · $7.00 input per 1M metered service tokens (no video input, 480p/720p only)
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head a805f17ab1ad…
COMPARE SEEDANCE 2.0