Pricing Plans

Number of Tokens monthly

Use the slider to estimate costs and see what bests fits you

Llama-3.1

Models

Cost / Million Tokens

Monthly Expense

Llama-3.1 (8B)

$ 0.15

Llama ( 8B)

Llama-3.1 (70B)

$ 0.90

Llama ( 8B)

Mistral

Model

Cost / Million Tokens

Monthly Expense

Mistral (7B)

$ 0.20

Llama ( 8B)

Whisper

Meta Models

Cost / Minute

Monthly Expense

Whisper

$ 0.003

Llama ( 8B)

SDXL

Number of Steps

Increasing steps leads to better quality and more detail in images.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Number of Images

Use this slider to estimate the number of images and the cost for your pay-as-you-go subscription.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Image Size

Cost / Image

Monthly Expense

512 x 512 px

$ 0.003

768 x 768 px

$ 0.003

1024 x 1024 px

$ 0.003

Flux-Dev (50 Inference Steps)

Image Size

Cost / Image

Cost / 1000 Images

512 x 512 px

$ 0.006

$ 6.00

768 x 768 px

$ 0.013

$ 13.00

1024 x 1024 px

$ 0.025

$ 25.00

Priced per minute. Pay only for the time your machine is running.

Host your own models on any machine with our optimised infrastructure. You can start or stop your instance any time using our Model Suite.

Hardware

GPUs

vCPUs

GPU RAM

RAM

Cost / Min

Nvidia T4 GPU

16 GB

32 GB

$ 0.01052

Nvidia L4 GPU

22 GB

32 GB

$ 0.014140

Nvidia A10G GPU

22 GB

32 GB

$ 0.024144

Nvidia A100 (40GB) GPU

16x

40 GB

144 GB

$ 0.06900

Nvidia A100 (80GB) GPU

16x

80 GB

144 GB

$ 0.08400

8x Nvidia H100 GPU

192x

640 GB

2048 GB

$ 1.331200

Our on-prem solutions are custom-made to address your specific use case and load profiles.

Please reach out to us at the email below if you are interested in exploring an on-prem solution.

If you would like to have an exploratory call with us, please use the book demo link and share some basic details with us.

For any other queries

contact@simplismart.ai