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.

deepseek + fireworks ai
4/27/2026

DeepSeek V4 Pro: Validating Frontier Models For Production

prevent prompt injection - blog title image
Developer Experience
4/24/2026

How we fixed prompt injection for all models on Fireworks

4/23/2026

Claude Code pricing: plans, API costs, and how to lower your bill

flywheel
Company News
4/6/2026

Own Your AI: Fireworks Training Preview

reinforcement-learning-loop
3/28/2026

The Fine-Tuning Bottleneck Isn't the Algorithm

delta-compressed-weight-updates
Developer Experience
3/22/2026

Frontier RL Is Cheaper Than You Think

Microsoft and Fireworks Partnership
Company News
3/8/2026

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

Hathora and Fireworks Partner Image
Company News
3/8/2026

Fireworks Acquires Hathora to Accelerate Global Compute Orchestration

inference providers vs api routers
3/6/2026

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

3/4/2026

The Best 8 LLM API Providers in 2026

3/2/2026

Best LLMs for coding in 2026

2/27/2026

The DeepSeek Model Lineup: V3.2, R1, and Distilled Variants Mapped to Production Workloads

The Benchmark Gap: What It Takes to Ship Kimi K2.5
2/3/2026

The Benchmark Gap: What It Takes to Ship Kimi K2.5

OpenClaw
Developer Experience
1/30/2026

The Missing Piece of the OpenClaw Mania: Truly ‘Own Your AI’ with Fireworks AI

Chart Showing Benchmarks
Developer Experience
1/27/2026

Build powerful agents on OSS models with Blazing Fast Inference on Fireworks

Kimi K 2p5
Model Releases
1/26/2026

Kimi K2.5 is Live on Fireworks: Vibe Coding, Agents, and Full-Parameter RFT

Turning Production Logs into Evaluation Dataset
Developer Experience
1/23/2026

Turning Production Logs into Evaluation Datasets: A Data-Driven Approach

1/13/2026

Best Open Source LLMs in 2026: We Reviewed 7 Models

DPO, your simplest RL pipeline with two rollouts
Developer Experience
12/31/2025

DPO, your simplest RL pipeline with two rollouts

Self-Improving Agents, Powered by Your Evals.
Developer Experience
12/17/2025

Self-Improving Agents, Powered by Your Evals

NVIDIA Nemotron 3 Nano on Fireworks: The Engine for Next-Generation AI Agents
Partner Announcements
12/15/2025

NVIDIA Nemotron 3 Nano on Fireworks: The Engine for Next-Generation AI Agents