Models / Alibaba

Alibaba

Deploy the latest Alibaba media models on Together AI. Wan for image and video generation and HappyHorse for cinematic, audio-synced video, served serverless.

Why Alibaba on Together AI?

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

Text, image, and reference to video

Alibaba's Wan and HappyHorse models cover text-to-video, image-to-video, and reference-to-video in one lineup, with native 1080p output and synchronized audio. Go from a prompt or still to a finished clip in a single call.

Leaderboard-topping video quality

HappyHorse has ranked #1 on independent text-to-video and image-to-video arenas on blind human preference, with lip sync across multiple languages. Wan adds fast, low-cost image generation to round out the pipeline.

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 Alibaba family

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

Image

Wan 2.6 Image

Video

HappyHorse 1.0 T2V

Video

HappyHorse 1.0 I2V

Video

HappyHorse 1.0 R2V

Video

HappyHorse 1.1 T2V

Video

HappyHorse 1.1 I2V

Video

HappyHorse 1.1 R2V

Video

Wan 2.7 Image-to-Video

Video

Wan 2.2 I2V

Video

Wan 2.2 T2V

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