Pricing
Starter
$0
+ compute costDesigned for small teams and independent developers aiming to elevate their capabilities.
Team
$100
+ compute costTailored for startups and larger organisations seeking rapid scalability
Enterprise
Custom
Ideal for large companies seeking extra security, support, and assurance, including the exclusive option for private VPC deployment to ensure a highly secure and tailored environment.
Inference pricing
Unlock the power of more than 50+ cutting-edge open-source models covering Chat, Language, Image, and Code with the SimpliML Inference API. Experience cost efficiency as you only pay for the precise usage of these advanced models. Elevate your product with unparalleled capabilities and budget-friendly innovation.
Experience unbeatable value with our pricing structure, tailored to your needs. Prices are per 1,000 tokens including input and output tokens for Chat, Language and Code models.
Dedicated Deployment
Elevate your model hosting experience with our innovative and groundbreaking approach. Say goodbye to hourly billing hassles – now, pay per second for GPU instances. Whether it is your fine-tuned tuned model, Opensource model or any other choice, our seamless transition to serverless deployment empowers you. Scale down to zero effortlessly, giving you unparalleled flexibility and cost-effectiveness. Take control of your hosting, one second at a time!
| Hardware Type | Price per hour (USD) | Model Size |
|---|---|---|
| L4 24GB | $0.90 | Up to 8B |
| A100 40GB Half (20GB) | $1.26 | Up to 8B |
| A100 40GB | $1.73 | 8.1B - 15B |
| A100 80GB | $2.16 | 15.1B - 30B |
| 2 x A100 80GB | $4.32 | 31B - 70B |
Fine-tuning pricing
Revolutionize your model refinement journey with SimpliML Fine-tuning. Tailor your models with precision and efficiency, paying per second for GPU instances.
| Hardware Type | Price per hour (USD) |
|---|---|
| A100 40GB | $1.73 |
| A100 80GB | $2.16 |
Interested in deploying or fine-tuning on your own cloud?
