Dedicated Container Inference
GPU infrastructure purpose-built for generative media workloads
Deploy video, audio, and avatar generation models on the AI Native Cloud.
Why Dedicated Container Inference with Together AI?
Designed for production workloads that need consistent performance and operational control.
Predictable pricing, leading unit economics
Leading performance lowers your effective GPU cost. Rapid autoscaling ensures you only pay for the capacity you use. Train on Together and deploy to dedicated containers without artifact transfer fees.
Research-backed speed
Hands-on partnership to profile and optimize your models. Achieve up to 2.6x speedup for production video generation workloads.
Made for massive surges
Proven elastic autoscaling during viral moments supports 10x plus traffic surges. Priority based queuing ensures paying customers never wait, even when free trial traffic spikes.
Key capabilities, purpose built for AI natives
From hardware to inference stack, every capability is optimized to get more out of every request.
Monitor inference jobs, GPU utilization, queue depth, and latency metrics in real time. Full observability for production debugging.
Autoscale rapidly to handle 10x traffic surges with zero failures. Keep critical workloads running via priority-based queuing.
Deploy video generation models across multiple GPUs with a simplified torchrun interface. No manual subprocess management required.
Configure infrastructure and dependencies in pyproject.toml, implement model logic via the Sprocket SDK, and push directly to GPU clusters. Bypass foundational orchestration setup completely.
Powered by leading research
With Dedicated Container Inference, teams benefit from our research pipeline from automatic kernel optimizations to hands-on profiling and tuning for workload-specific performance improvements.
Optimized Inference
together.compile
Throughput (TPS)
- Together dedicated container inference
- Previous provider
Together AI vs other providers
2.6x faster
Significant speedup of production video generation models through profiling and optimization, when compared with the next previous provider.
learn moreServer runtime
- inference (17 IMAGE resolutions x 3)
- Server start
together.compile vs alternatives
1.7x faster
together.compile automatically optimizes your kernel stack, delivering the fastest inference and near-instant server start and eliminating the tradeoff between compile-time optimization and cold start speed.
learn more
Deployment options
Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.
Real-time
A fully managed inference API that automatically scales with request volume.
Best for
Batch
Process massive workloads of up to 30 billion tokens asynchronously, at up to 50% less cost.
Best for
Dedicated Model Inference
An inference endpoint backed by reserved, isolated compute resources and the Together AI inference engine.
Best for
Dedicated Container Inference
Run inference with your own engine and model on fully-managed, scalable infrastructure.
Best for
Production-grade
security and data privacy
We take security and compliance seriously, with strict data privacy controls to keep your information protected. Your data and models remain fully under your ownership, safeguarded by robust security measures.
NVIDIA preferred partner
AICPA SOC 2 Type II
Customers running inference in production
“Together AI’s infrastructure has the capacity to soak up our viral moments without breaking a sweat. During major traffic surges, Dedicated Container Inference scales seamlessly while maintaining performance. And because we trained on Together’s Accelerated Compute, deploying to production was frictionless—one platform, zero artifact transfers, no deployment headaches.”
"Infrastructure costs can kill an AI company as they scale. Together's Dedicated Container Inference handles unpredictable viral traffic without over-provisioning and unlocked significant speedups that directly improved our unit economics—without sacrificing quality. This let us focus on building products instead of managing clusters."
Ledell Wu
Co-Founder & Chief Research Scientist, Creatify