Fireworks claims up to 1,500 tokens/sec on DeepSeek V4.1 Flash in Ultra-fast inference preview
Fireworks announced a set of enterprise AI products at its first annual Forge conference on November 3, 2026. The lead item is an Ultra-fast inference preview that the company says reached up to 1,500 tokens per second on DeepSeek V4.1 Flash. It also announced a private preview of Fireworks Sovereign for customer-owned infrastructure.
Fireworks announced a slate of enterprise AI products on November 3, 2026, at its first annual Forge conference. The lead item is an Ultra-fast inference preview that the company says reached up to 1,500 tokens per second on DeepSeek V4.1 Flash. The figure is Fireworks' own claim.
What was announced
- Ultra-fast inference: In public preview on NVIDIA Blackwell GPUs. Fireworks says it reached up to 1,500 tokens per second on DeepSeek V4.1 Flash.
- Fireworks Sovereign: A private preview of a offering for customer-owned infrastructure.
- Additional tools: Fireworks also announced tooling for model routing, evaluation and specialized serving.
The announcement is framed around matching inference speed and cost to the workload. Pricing, context window and other benchmark details were not part of the summary available at publication time, so they are not reported here. The coverage comes from Unite.AI.
What this means
Fireworks is pairing a speed claim on a specific model and hardware combination (DeepSeek V4.1 Flash on NVIDIA Blackwell) with deployment options for customers who want to run on infrastructure they own. The 1,500 tokens per second figure is a vendor-stated peak ("up to"), tied to a public preview, so teams evaluating it should test against their own workloads. The inclusion of routing, evaluation and specialized serving tools alongside the speed preview indicates Fireworks is positioning its platform around workload-specific configuration rather than a single serving tier.
Related Articles
Xcode 27.3 beta 1 adds GitHub Copilot to Apple's built-in coding assistant
Apple released Xcode 27.3 beta 1 on November 3, 2026, adding GitHub Copilot to the Xcode coding assistant. The beta also includes Swift 6.4, Device Hub improvements and UI testing support in Swift Testing. Xcode 27.3 is expected in December, according to 9to5Mac.
Moonshot AI's Kimi launches game development package with K3.1 agents inside Unity, Unreal Engine and Blender
Moonshot AI has released a game development and creative work solution built on the Kimi K3.1 model series, Kimi Code, Kimi Work and plugins for Unity, Unreal Engine and Blender. Kimi says one Unity demonstration ran for 20 hours without human intervention.
Xiaomi Humanoid Completes First 8-Hour Car Factory Shift; Xiaomi-Robotics-1 Enters Apartment Trial
Xiaomi says its humanoid robot worked an eight-hour shift at its car factory, covering the full daily production demand of the center console side-cover sorting station. The company also started a home-service trial of its Xiaomi-Robotics-1 embodied foundation model at a Xiaomi Youth Apartment.
Apple opens Siri AI to all third-party apps with 'app skills' in iOS 27.3 developer beta
Apple announced 'app skills' for Siri AI, allowing any app to create Siri AI integrations for the first time. The skills let apps teach Siri to coordinate complicated multi-step actions. The features arrive with iOS 27.3, macOS 27.3 and aligned releases, now in developer beta.
Comments
Loading...