Replicate

Cloud

Cloud for running open-source models. Easy API for Llama, Mistral, FLUX.

Provider Info

"API Env Var" REPLICATE_API_TOKEN

"Rate Limits" 6 req/min free, 3K RPM with payment

Llama 3.1 405B

Qwen 2.5 72B Coder

Mistral Large

FLUX.1 Pro

DeepSeek R1

Free

$0/mo

6 req/min

All models · Standard rate limits

Pay-as-you-go

$0/mo

Per-second pricing

All models · Higher concurrency

"Free Tier Available"

6 req/min free, 3K RPM with payment — No credit card required

affiliate

Replicate Affiliate Program

"Commission: Varies (one-time)"

"Join Program"