Fireworks AI On-Demand Deployments
Private deployments on reserved GPUs with no per-token rate limits.
| Hosting type | Dedicated endpoint |
|---|---|
| LLM models | Llama 3.3 70B Instruct, DeepSeek-V3, Qwen2.5 72B Instruct |
| Pricing range | |
| Pricing model | Per GPU-hour, Per second of GPU time |
| 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 Fireworks AI
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.
gpt-oss-120b is available on several serverless hosts
OpenAI's open-weight model can be called per token without running your own GPUs.