Together AI Dedicated Inference pricing
3 plans read from together.ai
Dedicated Inference — NVIDIA HGX H100 (on-demand)Priced on request On-demand, pay as you go; billed per GPU per hourSingle-tenant GPU instances · guaranteed performance (no sharing) · custom models · autoscaling and traffic spike handling Read 8 Oct 2026 · together.ai
Dedicated Inference — NVIDIA HGX B200 (on-demand)Priced on request On-demand, pay as you go; billed per GPU per hourSingle-tenant GPU instances · guaranteed performance (no sharing) · custom models · autoscaling and traffic spike handling Read 8 Oct 2026 · together.ai
Dedicated Inference — reserved capacityPriced on request Contact salesReserved GPU capacity · pricing depends on hardware and configuration Read 8 Oct 2026 · together.ai
In short
- Together AI Dedicated Inference has a free plan (Dedicated Inference — reserved capacity).
- Paid plans published: 2.
- 3 plans are priced on request (Dedicated Inference — NVIDIA HGX H100 (on-demand), Dedicated Inference — NVIDIA HGX B200 (on-demand), Dedicated Inference — reserved capacity).
What the alternatives costAll alternatives →
| Tool | From | Free plan | Free trial |
|---|---|---|---|
| Dify | $49.17/mo | Yes | No |
| Replit | $18/mo | Yes | No |
| Cursor | $20/mo | Yes | No |
| Bolt.new | $25/mo | Yes | No |
| Flowise | $35/mo | Yes | Yes |
| CrewAI AMP | — | Yes | No |
| Hugging Face Hub | $9/mo | Yes | No |
| LangChain | $39/mo | Yes | No |