Together AI Dedicated Endpoints
Reserved GPUs running the model you choose, for steady latency and throughput.
| Hosting type | Dedicated endpoint |
|---|---|
| LLM models | Llama 3.3 70B Instruct, Qwen2.5 72B Instruct, Llama 3.1 8B Instruct |
| Pricing range | |
| Pricing model | Per GPU-hour |
| Free tier available | No |
| Data center location | |
| Hardware / GPU options | Choice of data-center GPUs. List the current options here. |
| VRAM & memory | |
| Maximum model size | |
| OpenAI-compatible API | Yes |
News about Together AI
All news →Why we track hosting plans and models separately
The same model can cost and behave very differently depending on the plan you run it on.
Per token or per GPU-hour? Choose the billing model that fits your traffic
Spiky, low-volume traffic favours per-token plans. Steady, high-volume traffic often doesn't.
Review: Together AI Serverless Inference
A broad catalogue behind an OpenAI-compatible API makes this an easy place to start.
gpt-oss-120b is available on several serverless hosts
OpenAI's open-weight model can be called per token without running your own GPUs.