Models / ByteDance

ByteDance

Deploy the latest ByteDance models on Together AI. Seedance for cinematic video and Seedream for high-fidelity images, from ByteDance's Seed research lab.

Why ByteDance on Together AI?

Designed for production workloads that need 
consistent performance and operational control.

Cinematic video from text and images

ByteDance's Seedance models lead independent text-to-video and image-to-video arenas on blind human preference, with multi-shot consistency and camera control. Generate director-grade clips from a single API call.

High-fidelity images with accurate text

ByteDance's Seedream models deliver high-resolution images with sharp, accurate in-image text, ideal for posters, packaging, and branded creative. Pair them with Seedance to take a concept from still to motion.

Enterprise-ready from day one

SOC 2 Type II certified, HIPAA compliant, and deployed on US-based infrastructure. Full model ownership with no data retention by default.

Meet the ByteDance family

Explore top-performing models across text, image, video, code, and voice.

new

Video

ByteDance Seedance 2.5

Video

ByteDance Seedance 2.0

Image

Seedream 5.0 Lite

Video

ByteDance Seedance 1.0 Lite

Video

ByteDance Seedance 1.0 Pro

Coming Soon

Image

ByteDance SeedEdit

Image

ByteDance Seedream 4.0

Image

ByteDance Seedream 3.0

Deployment options

Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.

  • Serverless Inference

  • Provisioned 
Throughput

  • Dedicated Model 
Inference

  • Dedicated Container 
Inference

Serverless Inference

A fully managed real-time or batch inference API with access to dozens of the most popular AI models.

Best for

Variable or unpredictable traffic

Rapid prototyping and iteration

Cost-sensitive or early-stage production workloads

Provisioned 
Throughput

Reserved token capacity with SLA guarantees. Priced in PTUs, a normalized throughput unit. 

Best for

Production workloads

Reliability guarantees

Predictable pricing

Dedicated Model 
Inference

An inference endpoint backed by reserved, isolated compute resources and Together AI inference research.

Best for

Predictable or steady traffic

Latency-sensitive applications

High-throughput production workloads

Dedicated Container 
Inference

Run inference with your own engine and model on fully-managed, scalable infrastructure.

Best for

Generative media models

Non-standard runtimes

Custom inference pipelines