GroqCloud Developer Tier
Very fast token generation on Groq's LPU hardware, with a free tier to start.
| Hosting type | Serverless API |
|---|---|
| LLM models | Llama 3.3 70B Instruct, Llama 3.1 8B Instruct, gpt-oss-120b |
| Pricing range | |
| Pricing model | Pay per token |
| Free tier available | Yes |
| Data center location | |
| Hardware / GPU options | Groq LPU inference hardware. |
| VRAM & memory | |
| Maximum model size | |
| OpenAI-compatible API | Yes |
News about Groq
All news →gpt-oss-120b is available on several serverless hosts
OpenAI's open-weight model can be called per token without running your own GPUs.