Join us for our inaugural conference, Forge 2026

Fireworks Blog

Phylo and Fireworks

Phylo brings frontier AI to more scientists with open models on Fireworks

Phylo cut inference cost 60% while doubling users month-on-month, running Biomni Lab's long-horizon biology agents on open models on Fireworks.

Read More
Updated Supervised Fine Tuning
Model Releases6/13/2025

Introducing Supervised Fine Tuning V2

Reinforcement fine tuning announcement
Model Releases6/9/2025

Reinforcement Fine Tuning (Beta): Train expert open models to surpass closed frontier models

Fireworks Dev Day 2025 Wrapped
Company News5/29/2025

Fireworks DevDay 2025 Wrapped

Independent benchmarking of Fireworks shows >250 tokens / second on DeepSeek V3
Model Releases5/28/2025

FireAttention V4: Industry-Leading Latency and Cost Efficiency with FP4

Building an open-source Browser Agent on Fireworks
Developer Experience5/21/2025

Building an open-source Browser Agent on Fireworks

Agentic AI Systems
Developer Experience5/19/2025

Agentic AI Systems

Supervised Fine-Tuning (SFT) with LoRA on Fireworks: Tutorial
Developer Experience5/12/2025

Supervised Fine-Tuning (SFT) with LoRA on Fireworks: Tutorial

Qwen 3 on Fireworks
Model Releases5/6/2025

Qwen 3 on Fireworks: Controllable Chain-of-Thought and Tool Calling at Frontier Scale

Llama 4 Maverick on Fireworks
Developer Experience4/28/2025

Optimizing Llama 4 Maverick on Fireworks

RAG application using MongoDB Atlas and Fireworks
Developer Experience4/9/2025

Building Enterprise-Scale RAG Systems with Fireworks and MongoDB Atlas

Fireworks Now Supports NVIDIA NIM Deployments for Blazing AI Inference
Model Releases3/18/2025

Fireworks Now Supports NVIDIA NIM Deployments for Blazing AI Inference

Faster, more efficient DeepSeek on the Fireworks Developer Cloud
Model Releases3/18/2025

Faster, more efficient DeepSeek on the Fireworks Developer Cloud

Fine-Tuning DeepSeek v3 & R1 to optimize quality, latency, & cost
Model Releases3/12/2025

Fine-Tuning DeepSeek v3 & R1 to optimize quality, latency, & cost

Enabling Function Calling in DeepSeek v3: Bridging the Gap Between Text and Action
Model Releases2/14/2025

Enabling Function Calling in DeepSeek v3: Bridging the Gap Between Text and Action

DeepSeek v3 and R1 Model Architecture: Why it's powerful and economical
Developer Experience2/7/2025

DeepSeek v3 and R1 Model Architecture: Why it's powerful and economical

DeepSeek R1 Just Got Eyes with Fireworks Document Inlining
Model Releases2/5/2025

DeepSeek R1 Just Got Eyes with Fireworks Document Inlining

From text to task: Constrained generation for structured extraction in R1
Developer Experience2/1/2025

From text to task: Constrained generation for structured extraction in R1

Distillation with Reasoning: Can DeepSeek R1 Teach Better Than Humans?
Developer Experience1/31/2025

Distillation with Reasoning: Can DeepSeek R1 Teach Better Than Humans?

Mistral Small 3 Now Available on Fireworks: Faster, Lighter, and More Efficient
Model Releases1/30/2025

Mistral Small 3 Now Available on Fireworks: Faster, Lighter, and More Efficient

Beyond Supervised Fine Tuning: How Reinforcement Learning Empowers AI with Minimal Labels
Developer Experience1/27/2025

Beyond Supervised Fine Tuning: How Reinforcement Learning Empowers AI with Minimal Labels

DeepSeek R1: All you need to know 🐳
Model Releases1/24/2025

DeepSeek R1: All you need to know 🐳

Previous
Next