ByteDance Seedance 2.5 Flash Added to AI Gateway
·2026.11.16 09:00
Key point
The new model generates 4 to 30-second videos at up to 720p and 24 fps with synchronized audio from text or multimodal references.
Details
- ByteDance’s Seedance 2.5 Flash is now available on AI Gateway as a faster, lower-cost alternative to Seedance 2.5.
- Output quality matches the standard model in human realism, reference-based editing, and prompt adherence.
- Supports video generation with synchronized audio from text prompts or image, video, and audio references.
- Clips range from 4 to 30 seconds at up to 720p resolution and 24 frames per second in landscape, square, or portrait formats.
- Users can edit or extend existing videos and set first and last frames using provided images.
- Integration uses the bytedance/seedance-2.5-flash identifier with AI SDK 7, passing reference URLs via inputReferences.
Usage and Integration
- Reference images and videos are numbered separately in prompts as [Image 1] and [Video 1].
- Available for testing in the model playground or via the video generation quickstart.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.