bytedance/seedance-2.5

Seedance 2.5 generates a single-shot video of up to 30 seconds from a text prompt, with synchronised audio.

$0.22 / second
GPU: H100

Model Inputs

string

The text prompt used to generate the video

string

Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality.

string

Duration of the video in seconds. Supports 4 to 30 seconds, or auto to let the model decide based on the prompt.

string

The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.

boolean

Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.

string

Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate.

Result

Idle
Waiting for your input...

Pricing

bytedance/

seedance-2.5

You are billed for what this model actually produces — by the second — so a shorter request costs less and you never pay for idle time.

Rate
$0.22 / second
or
4 seconds / $1

For example, a request of 60 seconds costs about $13.20.

You are charged for what the request actually produces, so the final amount scales with the seconds you use.

ProviderPrice ($)Saving (%)
Synexa$1.10-
fal$1.10same price

Comparison prices are for an equivalent request.

Readme

Seedance 2.5 produces native single-shot video up to 30 seconds long at 480p, 720p or 1080p, from a text prompt alone.

Synchronised audio - sound effects, ambience and lip-synced speech - is generated by default and costs nothing extra. Set duration to auto to let the model pick a length that suits the prompt, and bitrate_mode to high for a larger, higher-quality encode.