Replicate API Pricing
Complete pricing for all Replicate models. Input/output costs per 1M tokens, context windows, and rate limits.
Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-05.
About cost estimation
Complete, recently synchronized token rates are not available for calculation. Check each row's billing units and source. To estimate Replicate alongside LLM models in a mixed workload, use the general spend calculator.
Open the spend calculator →Currently available rates
DeepSeek R1
LLMreplicate-deepseek-r1Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
1M tokens
$2.50
-
$8.00
—
—
—
FLUX 1.1 Pro
Image Genreplicate-flux-1.1-proPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
image
-
$0.04/image
-
—
—
—
FLUX.1 [dev]
Image Genreplicate-flux-devPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
image
-
$0.03/image
-
—
—
—
FLUX.1 [schnell]
Image Genreplicate-flux-schnellPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
image
-
$0.0030/image
-
—
—
—
Incredibly Fast Whisper
Audioreplicate-whisperPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
1M tokens
$0.35
-
$0.35
—
—
—
Llama 3.1 405B Instruct
LLMreplicate-llama-3.1-405bPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
1M tokens
$9.50
-
$9.50
—
—
—
Llama 3.1 70B Instruct
LLMreplicate-llama-3.1-70bPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
1M tokens
$0.95
-
$0.95
—
—
—
Stable Diffusion XL
Image Genreplicate-sdxlPlatform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Replicate
global
image
-
$0.0090/image
-
—
—
—
Replicate Overview
Products, apps, and recent changes
Replicate Changes
API changes, pricing updates, and deprecations
AI Cost Optimization
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.