Together AI Dedicated Inference

Spec sheet

Deployment

Customers select a target model and hardware configuration to deploy a production-ready endpoint, and Together says it can be live in minutes without deep infrastructure expertise.Read 8 Oct 2026 · together.ai

Support

The product FAQ directs users to contact Together's team for help, and the product page offers a Talk to Sales option.Read 8 Oct 2026 · together.ai

Headquarters

San Francisco, California, United StatesRead 28 Sep 2026 · together.ai

Founded

2022Read 28 Sep 2026 · together.ai

API compatibility

Dedicated and serverless inference use the same OpenAI-compatible API, so a serverless prototype can move to a dedicated endpoint by changing the endpoint.Read 8 Oct 2026 · together.ai

Autoscaling and routing

The product page lists SLO-driven autoscaling based on time to first token, latency, and throughput, along with least-loaded, session-affinity, and prefix-cache-aware routing.Read 8 Oct 2026 · together.ai

Best suited for

Together lists predictable or steady traffic, latency-sensitive applications, and high-throughput production workloads as best suited to Dedicated Model Inference.Read 8 Oct 2026 · together.ai

Company mission

Together AI describes its mission as designing a full-stack AI platform powered by systems research to help teams ship faster, scale reliably, and achieve superior unit economics.Read 8 Oct 2026 · together.ai

Compliance and data residency

Together says customers can choose a deployment region for data residency and identifies SOC 2 Type II and ISO 27001 as supporting certifications.Read 8 Oct 2026 · together.ai

Custom models

Customers can deploy custom or fine-tuned models from Hugging Face or their own S3 storage through the UI or CLI.Read 8 Oct 2026 · together.ai

Pricing basis

Dedicated Inference is billed per GPU-hour based on GPU type and replica count; the pricing page lists on-demand rates for HGX H100 and HGX B200, while reserved rates require contacting sales.Read 8 Oct 2026 · together.ai

Rollouts

Customers can test updated deployments with shadow traffic or A/B testing, and Together says it manages the rollout without taking the serving endpoint down.Read 8 Oct 2026 · together.ai

Security and privacy

Dedicated deployments use single-tenant, isolated GPUs; Together says traffic and data are not shared and that it does not train on customer prompts or model weights.Read 8 Oct 2026 · together.ai

Service

Dedicated inference runs a model on GPUs reserved exclusively for a customer's workload, providing consistent latency, predictable cost, and control over the model and hardware.Read 8 Oct 2026 · together.ai

Plans and prices

Every Together AI Dedicated Inference plan and price →

Where Specifiction places it

• Ai Development Tools#16 of 266.7