Parameters
| Name | Description | Type | Required | Enums |
|---|---|---|---|---|
| prompt | Description of the desired output. Recommended prompt length: under 1000 words. Lengthy text will lead to scattered information, and the model may ignore details and only focus on key points, resulting in missing elements in the generated video. | string | No | - |
| camera_fixed | Whether to keep the camera fixed during generation. | boolean | No | true, false |
| duration | Video duration in seconds (4-12 seconds). | integer | No | 4, 5, 6, 7, 8, 9, 10, 11, 12 |
| execution_expires_after | Task expiration time in seconds. | integer | No | - |
| first_frame_image | URL or Base64 data for the first frame image. | string | No | - |
| generate_audio | Whether to generate audio. 1.5 Pro exclusive feature. | boolean | No | true, false |
| last_frame_image | URL or Base64 data for the last frame image. | string | No | - |
| ratio | Aspect ratio of the generated video. | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive |
| resolution | Output resolution of the video. | string | No | 480p, 720p, 1080p |
| return_last_frame | Whether to return the last frame of the generated video. | boolean | No | true, false |
| seed | Random seed for reproducible generation. Use -1 for random. | integer | No | - |
| service_tier | Service tier for generation (e.g., default or flex). | string | No | default, flex |
Pricing
Unit: $/sec
| Dimension | Pricing |
|---|---|
| resolution: 1080p | 0.1200 |
| resolution: 480p | 0.0280 |
| resolution: 720p | 0.0597 |
Related Models
- bytedance/seedance-1.0-pro-fast-t2v: Seedance 1.0 Pro Fast inherits core advantages of the Pro model with 3x faster generation and 72% lower cost, balancing quality, speed, and price.
- bytedance/seedance-1.0-pro-t2v: ByteDance’s flagship text-to-video model with multi-shot narrative, superior semantic understanding, and cinematic 1080P output in diverse styles.
- bytedance/seedance-1.5-pro-t2v: Seedance 1.5 Pro supports audio-visual co-generation with multi-shot narrative, start/end frame control, and integrated audio output (voice, music, SFX).
- bytedance/seedance-1.0-pro-fast-i2v: Seedance 1.0 Pro Fast inherits core advantages of the Pro model with 3x faster generation and 72% lower cost, balancing quality, speed, and price.
- bytedance/seedance-1.0-pro-i2v: ByteDance’s flagship image-to-video model with multi-shot narrative, superior semantic understanding, and cinematic 1080P output in diverse styles.
- bytedance/seedance-2.0-fast-i2v: Faster variant of Dreamina Seedance 2.0 image-to-video. Accepts the same multimodal inputs as Seedance 2.0 I2V—text prompt plus optional reference images and audio—with lower latency. Resolution limited to 480p/720p.
- bytedance/seedance-2.0-i2v: Dreamina Seedance 2.0 image-to-video model. Generate video from a text prompt, optionally conditioned on a first or last frame, up to nine reference images, and up to three reference audio tracks. Outputs 480p, 720p, or 1080p with configurable aspect ratio.
- bytedance/seedance-2.0-fast-v2v: Faster variant of Dreamina Seedance 2.0 video-to-video. Accepts the same request body as Seedance 2.0 V2V but resolution limited to 480p/720p.
- bytedance/seedance-2.0-v2v: Dreamina Seedance 2.0 video-to-video model. Edit or extend one to three reference videos using a text prompt, with optional reference images, audio tracks, or frame images. Shares generation settings with Seedance 2.0 I2V.
