# Fireworks Forge: Ultra-fast inference preview, half-price Background Mode and Nexus Desktop

Canonical: https://theagenticweekly.com/news/fireworks-forge-ultra-fast-nexus-desktop · Evidence: Reported · First seen: 2026-11-03 19:58 UTC · Source published: not stated by the source · Brief published: 2026-11-03 21:07 UTC · Updated: 2026-11-03 21:07 UTC · Author: Agentic Weekly

> Fireworks announced a batch of launches at its Forge conference on November 3, 2026, led by Ultra-fast inference in public preview, which it says reaches "speeds up to 1,500 tokens per second" on DeepSeek V4.1 Flash. It also added a half-price Background Mode, Nexus Desktop with Pro plans from $8 a month, and serverless serving for trained LoRA adapters.

## What changed

- Ultra-fast inference on NVIDIA Blackwell GPUs is in public preview. Fireworks says it reaches up to 1,500 tokens per second on DeepSeek V4.1 Flash, and that a benchmarked 30-turn agent task fell from 1 minute to 8 seconds.
- Background Mode is a cheaper runtime at half price for work that can wait, such as eval data generation or overnight research. Fireworks also announced multi-day prompt caching and higher serverless rate limits (now generally available) for agents that pause and resume.
- Nexus Desktop joins the Nexus CLI and routes open and closed models inside the Codex app, Claude Desktop and OpenCode. Pro plans start at $8 per month and Teams at $10 per seat per month; Enterprise adds SSO, governance and shared budgets.
- Specialized Model Inference (public preview) serves trained LoRA adapters through the serverless API with per-token pricing and no charge while idle, starting with GLM 5.3 Flash. Training on Muse Glimmer 30B is free through November 30.
- No Eval (private preview) turns production traces into task-specific evaluations, and Fireworks Sovereign (private preview) runs its inference engine in a customer's own cloud or data center.
- Model governance, spending controls and exportable audit logs are now generally available, with regional data controls and customer-managed encryption in preview. Elastic Burst, which lets usage exceed its normal ceiling when spare capacity exists, is also generally available.

## In the source's words

> "in a benchmarked 30-turn agent task, completion time fell from 1 minute to 8 seconds at ultra-fast"
> (Fireworks AI, "Fireworks unveils new products at Forge", https://fireworks.ai/blog/fireworks-unveils-new-products-at-forge-to-help-companies-build-specialized-intelligence)

> "New Pro plans start at $8 per month, and Teams plans start at $10 per seat per month."
> (Fireworks AI, "Fireworks unveils new products at Forge", https://fireworks.ai/blog/fireworks-unveils-new-products-at-forge-to-help-companies-build-specialized-intelligence)

> "Fireworks already manages over 25,000 GPUs in customer environments."
> (Fireworks AI, "Fireworks unveils new products at Forge", https://fireworks.ai/blog/fireworks-unveils-new-products-at-forge-to-help-companies-build-specialized-intelligence)

## Early verdict

Most relevant to teams running multi-step agents on open models: Ultra-fast targets latency and Background Mode targets cost, but both are vendor-benchmarked and Ultra-fast is still a preview. (Basis: Based on the Fireworks announcement, which states the speed, half-price and preview status; we have not tested either mode.)

## What we have not verified

- We did not run Ultra-fast, Background Mode or Nexus; the 1,500 tokens per second and 1 minute to 8 seconds figures are Fireworks' own benchmarks.
- The post does not give per-token prices for Ultra-fast or say which models Background Mode covers beyond "eligible work".
- No Eval and Sovereign are private previews; we did not check who can get access or when they reach general availability.

## Timeline

- Source published: not stated by the source
- First seen by our watcher: 2026-11-03 19:58 UTC (via Fireworks blog)
- Brief published: 2026-11-03 21:07 UTC

## Sources

- [Fireworks blog: Fireworks unveils new products at Forge](https://fireworks.ai/blog/fireworks-unveils-new-products-at-forge-to-help-companies-build-specialized-intelligence) (primary source) (fetched 2026-11-03)

## Related

- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)

## How to cite

Agentic Weekly, "Fireworks Forge: Ultra-fast inference preview, half-price Background Mode and Nexus Desktop", published 2026-11-03 21:07 UTC, https://theagenticweekly.com/news/fireworks-forge-ultra-fast-nexus-desktop