Together AI exposes Seedance 2.5 through model ID ByteDance/Seedance-2.5. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Together AI SDK or REST API to call
ByteDance/Seedance-2.5— see the documentation for request format.
Code Examples
Install
pip install togetherAPI key
TOGETHER_API_KEYModel ID
ByteDance/Seedance-2.5Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
from together import Together
client = Together() # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
model="ByteDance/Seedance-2.5",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Capabilities
VisionMultimodalAudio
About Seedance 2.5
Seedance 2.5 is ByteDance Seed's audio-video joint generation model for up to 30s clips with heavy multimodal referencing and timestamp editing. Launched 2026-07-31 on Jimeng/Doubao; Vercel gateway id bytedance/seedance-2.5.
Model Specs
Released2026-07-31