Announcing our Series D and $1B ARR

Fireworks Blog

Headline Image Showing Why Routing Kimi K3 and Fable Outperforms the Rest

Kimi K3 is competitive with Fable; Kimi K3 + Fable is SoTA.

We ran both Kimi K3 and Fable 5 through ~1,000 agentic benchmark tasks. They tie on the overall top-line numbers, but specialize beneath the surface. K3 outperforms terminal and dev tooling, while Fable leads on web and multi-language tasks. Most importantly, we demonstrate that efficient routing between them improves overall accuracy and dramatically reducing token spend.

Understanding Embeddings and Reranking at Scale
Developer Experience
9/12/2025

Understanding Embeddings and Reranking at Scale

DeepSeek V3.1
Model Releases
8/26/2025

DeepSeek V3.1 now on Fireworks AI!

Eval Driven Development with Claude Code
Developer Experience
8/25/2025

LLM Eval Driven Development with Claude Code

Your AI Benchmark is Lying to You. Here's How We Caught It
Benchmarks
8/15/2025

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

Test driven agent development with eval protocol
Developer Experience
8/14/2025

Test-Driven Agent Development with Eval Protocol

Quality first: how Fireworks.ai is the go-to place for gpt-oss
Developer Experience
8/12/2025

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

GPT-OSS Models
Model Releases
8/5/2025

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

Eval Protocol
Model Releases
8/4/2025

Announcing Eval Protocol

Qwen 3 Decoded
Model Releases
8/1/2025

Qwen3 Decoded: Choosing the Right Model For Your Task

Kimi K2 Deep Dive
Developer Experience
8/1/2025

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

Fireworks AI Batch API
Model Releases
7/31/2025

Run bulk async workloads with Fireworks Batch API

Real-world leaderboard
Benchmarks
7/30/2025

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

Introducing Vision-Language Model Fine-tuning
Model Releases
7/29/2025

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

Notion
Case Studies
7/25/2025

How Notion Cuts Latency 4x and Scales Enterprise AI Workflows with Fireworks AI

QK-Clip
Developer Experience
7/22/2025

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 Releases
7/22/2025

VibeRL: When AI Trains AI

Sentient & Fireworks Powers Decentralized AI At Viral Scale
Case Studies
7/17/2025

Sentient & Fireworks Powers Decentralized AI At Viral Scale

Fireworks Sagemaker
Model Releases
7/15/2025

Fireworks AI Now Supports Amazon SageMaker

Deep-dive into MuonClip: Fixing Attention Score Explosions in Transformer Training
Developer Experience
7/15/2025

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

Understanding Function Calling: The Bridge to Agentic AI
Developer Experience
7/11/2025

Understanding Function Calling: The Bridge to Agentic AI

Using Model as Judge for Reward in Reinforcement Fine Tuning
Developer Experience
7/10/2025

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