Dedicated Inference — NVIDIA HGX H100 (on-demand)
Priced on request
Single-tenant GPU instances · guaranteed performance (no sharing) · custom models · autoscaling and traffic spike handling
Checked 8 Oct 2026
Plans and prices
Together AI Dedicated Inference pricing
Dedicated Inference — NVIDIA HGX B200 (on-demand)
Priced on request
Single-tenant GPU instances · guaranteed performance (no sharing) · custom models · autoscaling and traffic spike handling
Checked 8 Oct 2026
Dedicated Inference — reserved capacity
Priced on request
Reserved GPU capacity · pricing depends on hardware and configuration
Checked 8 Oct 2026