Join us for our inaugural conference, Forge 2026

Fireworks Blog

FireRouter with Opus

Introducing FireRouter with Opus

FireRouter with Opus routes routine turns to open models and keeps Claude Opus 5.5 for the turns that need it. 57% lower cost per session, cache-aware routing.

Read More
Your AI Benchmark is Lying to You. Here's How We Caught It
Benchmarks8/15/2025

Your AI Benchmark is Lying to You. Here's How We Caught It

Test driven agent development with eval protocol
Developer Experience8/14/2025

Test-Driven Agent Development with Eval Protocol

Quality first: how Fireworks.ai is the go-to place for gpt-oss
Developer Experience8/12/2025

Quality first: how Fireworks.ai is the go-to place for gpt-oss

GPT-OSS Models
Model Releases8/5/2025

Introducing OpenAI gpt-oss (20b & 120b)

Eval Protocol
Model Releases8/4/2025

Announcing Eval Protocol

Qwen 3 Decoded
Model Releases8/1/2025

Qwen3 Decoded: Choosing the Right Model For Your Task

Kimi K2 Deep Dive
Developer Experience8/1/2025

Kimi K2: Deep Dive into model performance and use-cases

Fireworks Batch API
Model Releases7/31/2025

Run bulk async workloads with Fireworks Batch API

Real-world leaderboard
Benchmarks7/30/2025

Fireworks Real-World Benchmarks: Find the Best OSS Model for the Job

Introducing Vision-Language Model Fine-tuning
Model Releases7/29/2025

Introducing Vision-Language Model Fine-tuning: Tailor VLMs to Your Domain

QK-Clip
Developer Experience7/22/2025

A Deep Dive into MLA training/inference difference and why QK-Clip from Kimi is such an elegant idea

VibeRL: When AI Trains AI
Model Releases7/22/2025

VibeRL: When AI Trains AI

Deep-dive into MuonClip: Fixing Attention Score Explosions in Transformer Training
Developer Experience7/15/2025

Deep-dive into MuonClip: Fixing Attention Score Explosions in Transformer Training

Fireworks Sagemaker
Model Releases7/15/2025

Fireworks Now Supports Amazon SageMaker

Understanding Function Calling: The Bridge to Agentic AI
Developer Experience7/11/2025

Understanding Function Calling: The Bridge to Agentic AI

Using Model as Judge for Reward in Reinforcement Fine Tuning
Developer Experience7/10/2025

Using Model-as-a-Judge for Reward in Reinforcement Fine Tuning

Flux Kontext on Fireworks
Model Releases7/9/2025

Introducing FLUX.1 Kontext on Fireworks

Announcing Response API with MCP
Model Releases6/22/2025

Unlock Your Tools: Fireworks Adds OpenAI-Response API with MCP Support (Beta)

Announcing Virtual Cloud on Fireworks
Model Releases6/16/2025

Build for Scale with Fireworks Virtual Cloud (GA)

Announcing Updated 3D FireOptimizer
Model Releases6/14/2025

3D FireOptimizer: Automating the Multi-Dimensional Tradeoffs in LLM Serving

Updated Supervised Fine Tuning
Model Releases6/13/2025

Introducing Supervised Fine Tuning V2

Previous
Next