# Fireworks announces faster agent inference and sovereign deployment

Digest AI · Enterprise & Industry · published 2026-11-03T21:16:02Z

Canonical: https://digestai.news/story/fireworks-announces-faster-agent-inference-and-sovereign-deployment

## Summary

Fireworks announced new enterprise AI products at its Forge conference on November 3, 2026, including an Ultra-fast inference preview that reached up to 1,500 tokens per second on DeepSeek V4.1 Flash. The company reported that completion time for its 30-turn agent benchmark fell from one minute to eight seconds with Ultra-fast. Fireworks also introduced a private preview of Fireworks Sovereign, which runs its inference engine in customer-owned infrastructure, and said it manages more than 25,000 GPUs in customer environments. Additional announcements included Nexus Desktop and Subscription Pricing, with Nexus Pro plans starting at $8 per month and Teams plans at $10 per seat per month, and specialized model inference entering public preview for serving LoRA adapters.

## Key points

- Ultra-fast inference reached up to 1,500 tokens per second on DeepSeek V4.1 Flash
- 30-turn agent benchmark completion time fell from one minute to eight seconds with Ultra-fast
- Fireworks Sovereign is in private preview and runs inference in customer-owned infrastructure

## Why it matters

These updates improve inference speed and cost efficiency for enterprise AI workloads, offering more control over deployment and better economics for long-running agents through caching and specialized serving.

## Sources

1. [Fireworks Announces Faster Agent Inference and Sovereign Deployment](https://unite.ai/fireworks-announces-faster-agent-inference-and-sovereign-deployment) (Unite.AI, 2026-11-03)

## Cite

Digest AI, "Fireworks announces faster agent inference and sovereign deployment", 3 November 2026, https://digestai.news/story/fireworks-announces-faster-agent-inference-and-sovereign-deployment

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/fireworks-announces-faster-agent-inference-and-sovereign-deployment.json