Stackd
Submit your tool
Back
Fireworks AI logo

Fireworks AI

Visit site

Fastest open-source model inference

Usage-basedLLM APIsLast verified: 2026-01-17

Overview

Fireworks AI provides fast inference for open-source models. Claims 4x faster than vLLM. SOC2/HIPAA compliant.

Works with

REST APIOpenAI compatiblePython

Pricing

MOST POPULAR
$0.20-1.20/1M tokensUsage
  • Fast inference
  • Open source models
  • Enterprise compliance

Pros

  • +Very fast inference
  • +SOC2/HIPAA
  • +Competitive pricing

Cons

  • -Open source models only

Find similar tools

Anthropic logo

Anthropic

Usage-based

Claude 4.5 family - Opus Sonnet Haiku

REST API+2
Cohere logo

Cohere

Free tier | Usage

Enterprise RAG and embeddings

REST API+2
Get Discovered by Developers

Promote your tool

Reach thousands of developers actively searching for AI tools. Featured listings get 10x more clicks.

Get in touch