# Fireworks AI

Check the cited vendor page before you rent from Fireworks AI.

Generative AI inference platform offering serverless per-token model APIs, fine-tuning and training, and on-demand GPU deployments on H100 to GB300 GPUs priced per GPU second.

## Details

- Address: Online, Global, United States
- Website: [fireworks.ai/](<https://fireworks.ai/>)
- GPU models: GB300, B300, B200, H200, H100
- Lowest on-demand H100 rate: 800 US cents/GPU-h
- Billing: per second
- Documentation: [docs.fireworks.ai/](<https://docs.fireworks.ai/>)
- Source note: Facts from the vendor's own website (https://fireworks.ai/pricing), fetched 2026-10-29.

## Questions

### Where is Fireworks AI?

Fireworks AI is at Online, Global, United States.

### How do I contact Fireworks AI?

To contact Fireworks AI, visit https://fireworks.ai/.

## Source

From [Vendor websites and documentation](https://fireworks.ai/pricing), license Facts compiled from public vendor pages. Source text and trademarks remain with their owners., checked 2026-10-29.

Last updated October 29, 2026.

## Links

- This GPU cloud provider on the [web page](<https://gpuclouds.fyi/us/global/online/fireworks-ai>)
- [Inference platforms in Online](<https://gpuclouds.fyi/us/global/online/category/inference-platforms.md>)
- [More GPU cloud providers in Online](<https://gpuclouds.fyi/us/global/online.md>)