Model detail
Doubao Seedance 2.5 Flash
Seedance 2.5 Flash generates or edits 480p and 720p video from text and multimodal references.
Model specs
- Model ID
-
doubao-seedance-2-5-flash-261115
- Context length
- –
- Max output
- –
- I/O modalities
- Released
- 2026-11
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /unit
Pricing updated
| Tier | Price /unit |
|---|---|
| lowres_video has_video | $4.3000 |
| lowres !(has_video) | $7.0000 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Video generation
Doubao Seedance 2.5 Flash is ByteDance's video generation model for text-to-video work. It accepts input such as text, image and video, and returns video. Its capabilities are broken down in the section just below. Render one short clip at your target resolution before planning a batch.
What should you check before using it?
Clips up to 30 seconds
Doubao Seedance 2.5 Flash generates clips up to 30 seconds long at 480p / 720p. Confirm that your target duration and resolution appear in those limits before you plan a render.
Why use it through MixRoute?
One MixRoute key reaches Doubao Seedance 2.5 Flash
One MixRoute key covers doubao-seedance-2-5-flash-261115, on the same account as the rest of the catalog. MixRoute supports calling Doubao Seedance 2.5 Flash through its OpenAI-compatible endpoint; point your client at https://api.mixroute.ai/v1 with the model ID doubao-seedance-2-5-flash-261115 and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Vision input
Doubao Seedance 2.5 Flash can process image inputs alongside text.
image_url content part alongside text messages.
09
FAQ
Doubao Seedance 2.5 Flash is a video generation model from ByteDance. It accepts text, image, video, audio and returns video.
More from ByteDance
All ByteDance modelsOne endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.