gpu pricing

Salad chops Cloud GPU pricing We are excited to announce that we have reduced the prices on our entire fleet of GPUs, making Salad the lowest priced cloud in the market – once again. You can view the updated GPU prices here or use this pricing calculator to estimate your savings with our new pricing. With these new prices, you can now rent an RTX 4090 from just $0.18/hr or an RTX 3090 from just $0.10/hr.  And these are not just advertised prices. Salad’s low pricing comes with unbeatable availability. With over 450,000 compute providers on the network today & growing, Salad can supply more GPUs at lower cost as you scale.  You can see the lowest GPU prices on Salad here. These prices are for the Batch Priority Tier, which is explained later in this post.  Why did we drop our prices?  At Salad, our goal has always been to democratize cloud computing by bringing the 100 Million+ latent consumer GPUs to the market at affordable prices. Since launching SaladCloud officially last September, a few things have changed:  Increased supply: We have over 450,000 GPUs contributing compute and 2 Million+ GPU owners who are part of our compute-providing ecosystem.  Customer feedback: We heard you loud and clear. Many Salad customers run batch workloads on 100s of GPUs. For this cohort, access to a high number of GPUs is more important than 24*7 availability.  Market dynamics: The GPU shortage has eased. This has led to lower GPU prices across other cloud providers (but with smaller scale).  Increased adoption: This one’s simple. Today, dozens of companies run their workloads on Salad.  How does the new pricing work?  In one word? Tiers. Priority tiers, to be specific.  There are now four pricing tiers: Batch (lowest) to High.  In this new priority tier system, where workloads compete for the best nodes based on their tier and therefore their pricing. The high priority tiers will be very close to our current pricing structure and the lower priority tiers will allow the Salad network to keep its price advantage. Higher the priority, higher the availability. Salad nodes are interruptible by default but we have a large pool of GPU providers who keep their GPUs online 24*7 for a premium price.  Example: An AI image generation tool requiring 100 GPUs 24*7 to serve inference to thousands of users will choose the highest priority pricing, ensuring round-the-clock availability.   Lower the priority, more the cost savings. Example: Deploying long-running workloads like signal processing or molecular dynamics in batch. You can see the updated pricing for different priority levels below.  How do I take advantage of this? That’s it. You are now on your way to scale without worries on SaladCloud while paying the lowest cost in the market. Contact us for even more cost savings For enterprise pricing and high-volume discounts: Email: [email protected] Website: portal.salad.com