tool listing

Fireworks AI

Serves open-weight models behind an API, billed per token on shared serverless capacity or per GPU-second on a dedicated deployment, with managed fine-tuning alongside.

Site
fireworks.ai
Category
inference
Pricing
usage-based: per-token for serverless inference, per-GPU-second for dedicated deployments, per-token for fine-tuning; free starter credit
Last verified
Wiki entry
Fireworks AI