Amux AI

ByteDance: Seedance 2.5

Active

Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up to 50 image, video, and audio reference assets, optional generated audio, and multilingual audiovisual generation.

Input:
Output:
Published:
2026-08-07
vision

Providers

Same model, different providers. Automatic routing spreads requests across healthy providers by default, or ranks them by price, latency and more.

Provider
Value30% offamux-special—
480p · With video input$6.4$4.48/1M tokens720p · With video input$6.4$4.48/1M tokens1080p · With video input$7$4.9/1M tokens480p · Without video input$10.7$7.49/1M tokens720p · Without video input$10.7$7.49/1M tokens1080p · Without video input$11.7$8.19/1M tokens
Read—Write—
————
Official14% offvolcengine—
480p · With video input$6.4$5.504/1M tokens720p · With video input$6.4$5.504/1M tokens1080p · With video input$7$6.02/1M tokens480p · Without video input$10.7$9.202/1M tokens720p · Without video input$10.7$9.202/1M tokens1080p · Without video input$11.7$10.062/1M tokens
Read—Write—
————

Availability

24 hours · 11/16–11/17

Success rate of requests sent by the Amux AI gateway to each provider. Client errors are excluded.

Activity

24 hours · 11/16–11/17

Relative request activity over time, broken down by serving provider. Indexed to the peak within the selected range (= 100); reflects trends and provider share, not absolute volume.

Related models

More models from ByteDance

ByteDance: Seedance 2.0 Mini2 providersSeedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It supports 480p and 720p output for 4-15 second videos. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024
ByteDance: Seedance 2.02 providersSeedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency, visual style, and camera movement from reference material. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024
ByteDance: Seedance 2.0 Fast2 providersSeedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost over maximum output quality. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024