News
Fireworks Unveils Faster AI Inference and Enterprise Tools
At Forge, Fireworks introduced ultra‑fast inference up to 1,500 tokens/sec, lower‑cost background processing, Nexus model access, and enterprise infrastructure tools.
News
At Forge, Fireworks introduced ultra‑fast inference up to 1,500 tokens/sec, lower‑cost background processing, Nexus model access, and enterprise infrastructure tools.