# Seedance 2.5

> ByteDance's newest video model, released through BytePlus ModelArk in October 2026. It makes clips of 4 to 30 seconds in one go, with sound, and can start from a picture.

- Maker: ByteDance (https://docs.byteplus.com/en/docs/modelark/create-video-generation-task-api)
- Type: Makes videos
- Clip length: 4 to 30 s
- Resolution: Up to 1080p
- Sound: yes, made with the video
- Can start from a picture: yes (on MultiScreenAI, Part 2 starts from the last frame of Part 1)

## Where to use it through an API

- BytePlus ModelArk: model id `dreamina-seedance-2-5-260628`, makes videos, up to 30 s

## Use it with every other AI at once

MultiScreenAI (https://www.multiscreenai.com) puts Seedance 2.5 on one screen next to ChatGPT, Claude, Gemini and 300+ models: one message goes to every panel, and a timed, blind test mode shows which answers best. Pro is free with a follow on X, and you use your own API keys.
AI agents and coding harnesses (Claude Code, Codex, Cursor, Gemini CLI) can ask Seedance 2.5 and other models at once through the MCP server at https://www.multiscreenai.com/api/mcp/ai; setup: https://www.multiscreenai.com/mcp