Together AI launches Provisioned Throughput (PTU) and cuts Dedicated Inference rates
Together AI launched a Provisioned Throughput (PTU) SKU at $0.05/PTU-min and cut Dedicated Inference rates — on-demand H100 to $5.49/hr, B200 to $8.99/hr.
No reserved-throughput product; Dedicated Inference priced per instance — 1x H100 80GB $6.49/hr, 1x HGX B200 180GB $11.95/hr, H200 Contact us.
New Provisioned Throughput SKU reserves capacity in throughput units at $0.05/PTU-minute (MiniMax M3, GLM-5.2); Dedicated Inference restructured to per-GPU-per-hour, on-demand vs reserved — on-demand H100 $5.49/hr, B200 $8.99/hr, with H200/B300/GB200/GB300 quoted Contact us and all reserved capacity Contact sales.
Proof of change
Together AI's pricing pages, as we captured them on two dates.
Showing the whole page as captured — scroll either panel, or open it at full size.
Show 3 other pages we compared
Showing the whole page as captured — scroll either panel, or open it at full size.
Showing the whole page as captured — scroll either panel, or open it at full size.
Showing the whole page as captured — scroll either panel, or open it at full size.
Both images are our own captures, taken on the dates shown. The pixels are unmodified — nothing is retouched, and where a region is highlighted the marker is drawn over the image, not into it. Open either capture to see it at full resolution.
Together AI added a fifth pricing surface, Provisioned Throughput (PTU), which reserves dedicated inference capacity in throughput units billed per PTU-minute ($0.05/PTU-min on MiniMax M3 and GLM-5.2). Each PTU delivers a fixed, model-specific tokens-per-minute rate, and an on-page calculator sizes the PTUs required for a traffic profile and estimates monthly cost and savings versus a commercial model’s list price (assuming 24/7 provisioning).
In the same update, Dedicated Inference was restructured from a per-instance table into a per-GPU-per-hour grid split into on-demand (pay-as-you-go) and reserved (Contact sales) columns. On-demand HGX H100 dropped from $6.49 to $5.49/hr (-15%) and HGX B200 from $11.95 to $8.99/hr (-25%), while newly listed HGX H200, HGX B300, GB200 NVL72, and GB300 NVL72 lines are quoted “Contact us”. Serverless per-token and GPU Cluster rates were unchanged. The pricing page also carries a new Series C funding banner.
Together launched Provisioned Throughput — a new SKU that reserves dedicated capacity in throughput units (PTUs) billed per PTU-minute ($0.05/PTU-min on MiniMax M3 and GLM-5.2), with an on-page calculator that sizes PTUs and estimates monthly cost vs. commercial-model list prices. In the same update, Dedicated Inference was restructured to a per-GPU-per-hour table split into on-demand (pay-as-you-go) vs reserved (Contact sales) columns: on-demand HGX H100 fell to $5.49/hr (from $6.49) and HGX B200 to $8.99/hr (from $11.95), and NVIDIA HGX H200, HGX B300, GB200 NVL72, and GB300 NVL72 lines were added (quoted "Contact us"). GPU Cluster and serverless rates were unchanged. The pricing page also carries a new Series C funding banner.