RunPod Serverless
Run your own container or a ready-made vLLM worker on GPUs that scale with requests.
| Hosting type | Serverless GPU |
|---|---|
| LLM models | Llama 3.1 8B Instruct, Llama 3.3 70B Instruct, Qwen2.5 72B Instruct, gpt-oss-120b |
| Pricing range | |
| Pricing model | Per second of GPU time |
| Free tier available | No |
| Data center location | |
| Hardware / GPU options | Wide range of consumer and data-center GPUs. |
| VRAM & memory | |
| Maximum model size | |
| OpenAI-compatible API | No |
News about RunPod
All news →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: RunPod Serverless for open models
Flexible and inexpensive at low volume, but you own the container and the cold starts.