Serverless 2.0 is live: control reliability & speed without reserved capacity. Get Started.

Fireworks Blog

nemotron 3 benchmarks

NVIDIA Nemotron 3 Ultra is live on Fireworks, day zero

Run NVIDIA Nemotron 3 Ultra today. Optimize autonomous agents with 1M context and frontier reasoning. Day-zero support on the fastest infrastructure.

Filters

Open-source agents with frontier advisors

Open-source agents with frontier advisors: matching frontier performance through training and harness engineering

Fireworks x Trilogy

Trilogy Validates Open-Weight AI Models for Enterprise AI Workloads with Fireworks

Serverless 2.0: Three Ways to Run Inference, One API

Serverless 2.0: Three Ways to Run Inference, One API

Notte x Fireworks Benchmark Report

Case Studies5/20/2026

Agents Don't Fail on Intelligence. They Fail on Execution.

Innovative Solutions Rebuilds Enterprise Services Delivery with Fireworks AI

Case Studies5/5/2026

Innovative Solutions Rebuilds Enterprise Services Delivery with Fireworks AI

deepseek + fireworks ai

DeepSeek V4 Pro: Validating Frontier Models For Production

Notes on DeepSeek-V4's training system

prevent prompt injection - blog title image

Developer Experience4/24/2026

How we fixed prompt injection for all models on Fireworks

flywheel

Company News4/6/2026

Own Your AI: Fireworks Training Preview

Scaling and Optimizing Frontier Model Training

Scaling and Optimizing Frontier Model Training

reinforcement-learning-loop

The Fine-Tuning Bottleneck Isn't the Algorithm

Frontier RL Is Cheaper Than You Think

Frontier RL Is Cheaper Than You Think

Training-Inference Parity in MoE Models: Where Numerics Drift

Training-Inference Parity in MoE Models: Where Numerics Drift

Microsoft and Fireworks Partnership

Company News3/8/2026

Introducing Fireworks on Microsoft Foundry: Bringing Best-in-Class Open Model inference to Azure

Hathora and Fireworks Partner Image

Company News3/8/2026

Fireworks Acquires Hathora to Accelerate Global Compute Orchestration

inference providers vs api routers

Inference Providers vs. API Routers: where do tokens come from?