Replicate

Claude 4.5 family - Opus Sonnet Haiku

Anthropic

Claude 4.5 family - Opus Sonnet Haiku

Cerebras

REST APIOpenAI compatible

Ultra-fast LLM inference powered by wafer-scale chips

Cerebras

Ultra-fast LLM inference powered by wafer-scale chips

REST API+1

Get Discovered by Developers

Promote your tool

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

Back

Replicate

Visit site

1000+ models via simple API

Usage-basedLLM APIsLast verified: 2026-01-18

Overview

Replicate hosts thousands of open-source and proprietary ML models with simple API access. Pay per compute second or per output depending on model.

Works with

REST API

Pricing

$3/$15 per MTokClaude 3.7 Sonnet

Hybrid reasoning model
Via Replicate API

$3.75/$10 per MTokDeepSeek R1

Reasoning model
On par with o1

POPULAR

$0.003/imageFLUX Schnell

Fastest FLUX model
Local dev friendly

$0.025/imageFLUX Dev

12B parameter model
High quality

Pros

+Huge model selection (1000+)
+Simple API
+Pay only for what you use
+Image/video/audio/LLM models
+Deploy custom models with Cog

Cons

-Can get expensive at scale
-Cold starts on some models
-Joining Cloudflare (transition period)

Find similar tools

Anthropic

Claude 4.5 family - Opus Sonnet Haiku

Anthropic

Claude 4.5 family - Opus Sonnet Haiku

Cerebras

REST APIOpenAI compatible

Ultra-fast LLM inference powered by wafer-scale chips

Cerebras