Show HN: Salad, a distributed cloud for AI (like Airbnb for GPUs)

https://salad.com/

The orchestration cloud

Salad orchestrates the world's idle GPUs.

One orchestration layer for containers, tokens, and GPUs, running across 16,000+ daily active GPUs in 190+ countries, or privately inside your own organization. Up to 90% less than hyperscaler pricing.

No contracts, no minimums, per-second billing on SaladCloud. Reserved capacity and private deployments available for enterprise.

# Deploy a container group to 40 GPUs across the network
curl -X POST https://api.salad.com/api/public/organizations/acme/projects/prod/containers \
  -H "Salad-Api-Key: $SALAD_API_KEY" \
  -H "Accept: application/json" \
  -H "Content-Type: application/json" -d '{
    "name": "inference",
    "display_name": "Inference",
    "container": { "image": "ghcr.io/acme/inference:latest",
                   "resources": { "cpu": 4, "memory": 8192, "gpu_classes": ["9998fe42-04a5-4807-b3a5-849943f16c38"] },
                   "priority": "high" },
    "replicas": 40, "autostart_policy": true, "restart_policy": "always"
  }'
# → 40 replicas scheduled onto RTX 4090 nodes worldwide. Billing starts only when each instance is running.

Running in production at

CivitaiBlendKlyne.ai Undetectable AIParetoDatasembly

16,000+daily active GPUs

190+countries with nodes

90%lower cost vs. hyperscalers

$0.015per GPU-hour, starting price

Platform and deployment options

One orchestration layer, across every pool.

Use a managed token API, deploy containers through Salad Container Engine, or choose the infrastructure that fits. Community Cloud is the on-demand GPU pool; Dedicated provides reserved hardware; Private Cloud runs the same orchestration inside your organization.

Managed token API

AI Gateway

An OpenAI-compatible endpoint for open-weight models, served from the network. Pay per token or request a flat monthly plan; your data is never used for training.

openai apiqwen262k ctx

Learn more →

Core orchestration

Salad Container Engine

The software layer that schedules, monitors, and reallocates Docker workloads across distributed GPU pools. Use it on Community Cloud, Dedicated, or your own fleet.

docker10,000+ replicasfailover

Explore the engine →

Dedicated infrastructure

Salad Dedicated

Reserved bare metal and virtual machines on contract. RTX PRO 6000 Blackwell first, with thousands of cards coming online.

rtx pro 6000bare metalcontracts

Explore Dedicated →

On-demand infrastructure

Community Cloud

The distributed pool of idle consumer GPUs that Salad Container Engine deploys onto, with priority pricing and capacity across 190+ countries.

rtx 5090rtx 4090from $0.015/hr

Pricing & availability →

Why Salad

Two competencies, nine years, one platform.

Most clouds operate uniform racks in a few data centers. Salad was built to turn diverse hardware across thousands of locations into dependable, usable infrastructure.

Orchestration across distributed infrastructure

Salad Container Engine schedules OCI containers onto nodes it has never seen before, verifies them, isolates them behind a hypervisor, streams logs, and reallocates work the moment a node disappears. It runs identically on consumer PCs, workstation fleets, and data-center servers.

Orchestration across idle GPUs

450,000+ GPUs have contributed to the network since 2018. A proprietary trust rating scores node performance and availability; priority pricing matches interruptible supply to workloads designed for it. The result is a GPU pool with exceptional scale, utilization, and economics.

Economics no data center can match

The hardware already exists. Salad coordinates supply instead of financing new data-center capacity, creating a structurally lower cost base and helping customers run substantially more work within the same budget.

Hands-on engineering support

Production customers work directly with Salad engineers on architecture, container tuning, and cost. Volume deployments and committed contracts receive tailored support and pricing.

Where it runs

SaladCloud, or a private cloud on your own devices.

SaladCloud

Deploy on the global network. Community Cloud for the lowest cost anywhere; Salad Dedicated for reserved capacity on contract. Same API, same portal, same orchestration.

Dotted world map with node markers across North and South America, Europe, Africa, Asia and Oceania
Nodes in 190+ countries. Markers are representative metros, not a live node feed.

Explore the platform →

Private Cloud

Run Salad's orchestration stack inside your organization. Pool the idle GPUs in workstations and servers you already own into a private, OpenAI-compatible token service. Company data never leaves company devices.

An organization's own machines pooled behind a single private endpoint Learn more →

Optimized per workload

Every modality, tuned for the network.

Published benchmarks, not promises. Each figure links to the methodology.

Image generation

5,243 Flux.1-Schnell images per dollar. Civitai serves 10 million images a day on 600+ Salad GPUs.

Image generation →

Transcription

95.1% accuracy on CommonVoice, the top of the benchmark, from $0.16 per audio hour.

Transcription API →

Text-to-speech

Up to 6 million words per dollar with OpenVoice on RTX-class GPUs.

Voice AI →

LLM inference

Flat hourly GPUs for agents and RAG, or per-token pricing through AI Gateway from $0.06 per million input tokens.

AI Gateway →

Computer vision

309,000 images tagged per dollar with RAM++; YOLOv8 object detection for 73% less than Azure.

Computer vision →

Batch & simulation

1,000,000 hours of audio transcribed for $1,260; GROMACS at 90%+ below data-center pricing.

Batch processing →

Customer stories

Teams ship on Salad.

Civitai

"By switching to SaladCloud, we are serving inference on over 600 consumer GPUs to deliver 10 Million images per day and training more than 15,000 LoRAs per month. SaladCloud not only had the lowest GPU prices in the market but also offered us incredible scalability."

Justin Maier · Founder & CEO, CivitaiRead the case study →

Blend

"On SaladCloud's consumer GPUs, we are running 3X more scale at half the cost of A100s on our local provider and almost 85% less cost than the two major hyperscalers we were using before. I'm not losing sleep over scaling issues anymore."

Jamsheed Kamardeen · CTO, BlendRead the case study →

Klyne.ai

"If you want access to 1000s of GPUs, you can get them on SaladCloud for better cost-efficiency. Salad is also really customer friendly, something you cannot get from a larger cloud provider as a startup."

Zachary Lawrence · CEO, Klyne.aiRead the case study →

From the blog

How to build on Salad.

Benchmarks, tutorials, and product updates.

All posts

What kind of GPUs are on SaladCloud?

NVIDIA RTX-class consumer GPUs, from the RTX 3060 through the RTX 5090 (32 GB), plus selected AMD classes. Every GPU is benchmarked before it is admitted and continuously scored by our trust rating. Data-center and workstation GPUs, starting with the RTX PRO 6000 Blackwell, are available on contract through Salad Dedicated.

How is this different from a spot instance?

Community Cloud nodes are interruptible, like spot, and priced by priority tier (High, Medium, Low, Lowest). Unlike spot, Salad Container Engine handles the consequences: it reallocates your workload to another node of the same class automatically, bills only for running time, and never charges for cold start or image download.

How does security work on a network of other people's computers?

Your container runs inside a Linux virtual machine partitioned from the host by a hypervisor, with image, configuration, and traffic encrypted in transit and at rest. Host-intrusion detection destroys the environment and blacklists the machine if anything attempts to access it. Salad is SOC 2 Type I compliant. Read the security overview.

What workloads are not a fit?

Anything that needs sub-10-millisecond latency, multi-GPU NVLink training, or data-residency guarantees that a consumer network cannot provide. For those requirements, Salad Dedicated offers reserved hardware and Private Cloud runs on your own infrastructure. Our engineers are available to support the deployment choice and architecture.

Why do people share their GPUs with Salad?

They earn. Salad Chefs run our desktop app when their PC is idle and redeem Salad Balance for PayPal, games, gift cards, and more. Since 2018, more than 450,000 GPUs have contributed compute to the network. Learn about becoming a Chef.

Can we run Salad's technology inside our own company?

Yes. Private Cloud deploys Salad's orchestration stack on your infrastructure and pools the idle GPUs in your existing workstations and servers into a private, OpenAI-compatible endpoint. Prompts, completions, and embeddings never leave your network.

Explore Salad today.

Deploy on SaladCloud, or talk to sales about reserved and private options.

{
"by": "bobjmiles",
"descendants": 0,
"id": 40248345,
"score": 1,
"text": "Hey HN! Bob here, Founder and CEO of Salad ([www.salad.com](<a href=\"http:&#x2F;&#x2F;www.salad.comwww.salad.com\" rel=\"nofollow\">http:&#x2F;&#x2F;www.salad.comwww.salad.com</a>)), a distributed cloud for AI inference at scale.<p>*Why Salad?* Because there’s 400 Million consumer GPUs in the world (~100 Million AI-enabled RTX GPUS) and most of them lie unused for 18-22 hrs a day.<p>These consumer GPUs offer similar or better cost-performance than high-end AI GPUs for many AI&#x2F;ML use cases (Speech-to-text, batch jobs, text-to-image, computer vision to name a few).<p>With Salad, we have activated this latent compute in everyday PCs to power AI&#x2F;ML workloads.<p>*How big is our network?* More than 1,900,000 individual PC owners on the network. Around 10K+ GPUs (RTX&#x2F;GTX series) are running AI workloads from companies at any given time.<p>*What’s in it for AI companies &amp; data scientists?*<p>Users get GPUs at the lowest market price with high scalability<p>*What’s in it for people sharing GPU time?*<p>GPU owners get rewards ranging $20 - $180 depending on the GPU type (Higher vRAM GPUs earn more). These rewards can be exchanged in our marketplace for gift cards, games and more.<p>*How are our prices?*<p>GPU prices start from $0.02&#x2F;hour and across different consumer GPUs, we have the lowest price and largest scale in the market.<p>For ex, an RTX 3080Ti for AI transcription costs $0.0012&#x2F;hour with a self-managed OS model on Salad. The next best cost in the market is an API ($0.28&#x2F;hr).<p>*Who can run on SaladCloud today?*<p>Here are the best fits for our infra today:<p>(1) Needs &gt;3 GPUs running 24*7<p>(2) AI inference workloads or batch processing<p>(3) No compliance-related workloads (HIPAA, etc) or highly sensitive&#x2F;proprietary data<p>As a distributed cloud, we are workload-agnostic. That being said, with our current features &amp; team, we are best poised to support AI&#x2F;ML workloads. As we grow, we will add more support for other workloads.<p>We’re happy to offer $1000 in free credits if you have a demand for more than 10 GPUs per month running consistently.<p>Just sign up for a demo call and select ‘HackerNews’ in the ‘How did you hear about us?’ field.<p>Book a call to discuss your use case: <a href=\"https:&#x2F;&#x2F;salad.com&#x2F;get-a-demo\" rel=\"nofollow\">https:&#x2F;&#x2F;salad.com&#x2F;get-a-demo</a><p>Signup for SaladCloud here: <a href=\"https:&#x2F;&#x2F;portal.salad.com&#x2F;\" rel=\"nofollow\">https:&#x2F;&#x2F;portal.salad.com&#x2F;</a><p>To earn with your PC, download the Salad app here: <a href=\"https:&#x2F;&#x2F;salad.com&#x2F;download\" rel=\"nofollow\">https:&#x2F;&#x2F;salad.com&#x2F;download</a><p>GitHub Repo: <a href=\"https:&#x2F;&#x2F;github.com&#x2F;SaladTechnologies\">https:&#x2F;&#x2F;github.com&#x2F;SaladTechnologies</a><p>Our mission is to democratize cloud computing with a fully people-powered cloud and helping companies break free from the cloud monopoly!",
"time": 1714747893,
"title": "Show HN: Salad, a distributed cloud for AI (like Airbnb for GPUs)",
"type": "story",
"url": "https://salad.com/"
}
{
"author": null,
"date": null,
"description": "SaladCloud orchestrates AI workloads across 16,000+ daily active GPUs in 190+ countries. Save up to 90% vs hyperscalers, or run our stack on your own infrastructure.",
"image": "https://salad.com/img/og-default.png",
"logo": null,
"publisher": "Salad",
"title": "Salad — Orchestration for distributed infrastructure and the world’s idle GPUs",
"url": "https://salad.com/"
}
{
"url": "https://salad.com/",
"title": "Salad — Orchestration for distributed infrastructure and the world's idle GPUs",
"description": "The orchestration cloudSalad orchestrates the world's idle GPUs.One orchestration layer for containers, tokens, and GPUs, running across 16,000+ daily active GPUs in 190+ countries, or privately inside your...",
"links": [
"https://salad.com/"
],
"image": "https://salad.com/img/og-default.png",
"content": "<div><div><p><span>The orchestration cloud</span></p><h2>Salad orchestrates <span><span>the world's idle GPUs.</span></span></h2><p>One orchestration layer for containers, tokens, and GPUs, running across 16,000+ daily active GPUs in 190+ countries, or privately inside your own organization. Up to 90% less than hyperscaler pricing.</p><p>No contracts, no minimums, per-second billing on SaladCloud. Reserved capacity and private deployments available for enterprise.</p></div><div><pre><span># Deploy a container group to 40 GPUs across the network</span>\n<span>curl</span> -X POST https://api.salad.com/api/public/organizations/acme/projects/prod/containers \\\n -H <span>\"Salad-Api-Key: $SALAD_API_KEY\"</span> \\\n -H <span>\"Accept: application/json\"</span> \\\n -H <span>\"Content-Type: application/json\"</span> -d <span>'{\n \"name\": \"inference\",\n \"display_name\": \"Inference\",\n \"container\": { \"image\": \"ghcr.io/acme/inference:latest\",\n \"resources\": { \"cpu\": 4, \"memory\": 8192, \"gpu_classes\": [\"9998fe42-04a5-4807-b3a5-849943f16c38\"] },\n \"priority\": \"high\" },\n \"replicas\": 40, \"autostart_policy\": true, \"restart_policy\": \"always\"\n }'</span>\n<span># → 40 replicas scheduled onto RTX 4090 nodes worldwide. Billing starts only when each instance is running.</span></pre></div><div><p><span>Running in production at</span></p><p><span>Civitai</span><span>Blend</span><span>Klyne.ai</span>\n<span>Undetectable AI</span><span>Pareto</span><span>Datasembly</span></p></div><div><p><b>16,000+</b><span>daily active GPUs</span></p><p><b>190+</b><span>countries with nodes</span></p><p><b>90%</b><span>lower cost vs. hyperscalers</span></p><p><b>$0.015</b><span>per GPU-hour, starting price</span></p></div><div><div><p><span>Platform and deployment options</span></p><h2>One orchestration layer, across every pool.</h2><p>Use a managed token API, deploy containers through Salad Container Engine, or choose the infrastructure that fits. Community Cloud is the on-demand GPU pool; Dedicated provides reserved hardware; Private Cloud runs the same orchestration inside your organization.</p></div><div><div><p><span>Managed token API</span></p><h3>AI Gateway</h3><p>An OpenAI-compatible endpoint for open-weight models, served from the network. Pay per token or request a flat monthly plan; your data is never used for training.</p><p><span>openai api</span><span>qwen</span><span>262k ctx</span></p><p><a target=\"_blank\" href=\"https://salad.com/ai-gateway\">Learn more →</a></p></div><div><p><span>Core orchestration</span></p><h3>Salad Container Engine</h3><p>The software layer that schedules, monitors, and reallocates Docker workloads across distributed GPU pools. Use it on Community Cloud, Dedicated, or your own fleet.</p><p><span>docker</span><span>10,000+ replicas</span><span>failover</span></p><p><a target=\"_blank\" href=\"https://salad.com/salad-container-engine\">Explore the engine →</a></p></div><div><p><span>Dedicated infrastructure</span></p><h3>Salad Dedicated</h3><p>Reserved bare metal and virtual machines on contract. RTX PRO 6000 Blackwell first, with thousands of cards coming online.</p><p><span>rtx pro 6000</span><span>bare metal</span><span>contracts</span></p><p><a target=\"_blank\" href=\"https://salad.com/dedicated\">Explore Dedicated →</a></p></div><div><p><span>On-demand infrastructure</span></p><h3>Community Cloud</h3><p>The distributed pool of idle consumer GPUs that Salad Container Engine deploys onto, with priority pricing and capacity across 190+ countries.</p><p><span>rtx 5090</span><span>rtx 4090</span><span>from $0.015/hr</span></p><p><a target=\"_blank\" href=\"https://salad.com/pricing\">Pricing &amp; availability →</a></p></div></div></div><div><div><p><span>Why Salad</span></p><h2>Two competencies, nine years, one platform.</h2><p>Most clouds operate uniform racks in a few data centers. Salad was built to turn diverse hardware across thousands of locations into dependable, usable infrastructure.</p></div><div><div><h3>Orchestration across distributed infrastructure</h3><p>Salad Container Engine schedules OCI containers onto nodes it has never seen before, verifies them, isolates them behind a hypervisor, streams logs, and reallocates work the moment a node disappears. It runs identically on consumer PCs, workstation fleets, and data-center servers.</p></div><div><h3>Orchestration across idle GPUs</h3><p>450,000+ GPUs have contributed to the network since 2018. A proprietary trust rating scores node performance and availability; priority pricing matches interruptible supply to workloads designed for it. The result is a GPU pool with exceptional scale, utilization, and economics.</p></div><div><h3>Economics no data center can match</h3><p>The hardware already exists. Salad coordinates supply instead of financing new data-center capacity, creating a structurally lower cost base and helping customers run substantially more work within the same budget.</p></div><div><h3>Hands-on engineering support</h3><p>Production customers work directly with Salad engineers on architecture, container tuning, and cost. Volume deployments and committed contracts receive tailored support and pricing.</p></div></div></div><div><div><p><span>Where it runs</span></p><h2>SaladCloud, or a private cloud on your own devices.</h2></div><div><div><h3>SaladCloud</h3><p>Deploy on the global network. Community Cloud for the lowest cost anywhere; Salad Dedicated for reserved capacity on contract. Same API, same portal, same orchestration.</p><figure><img src=\"https://salad.com/img/world-nodes.svg\" alt=\"Dotted world map with node markers across North and South America, Europe, Africa, Asia and Oceania\" /><figcaption>Nodes in 190+ countries. Markers are representative metros, not a live node feed.</figcaption></figure><p><a target=\"_blank\" href=\"https://salad.com/products\">Explore the platform →</a></p></div><div><h3>Private Cloud</h3><p>Run Salad's orchestration stack inside your organization. Pool the idle GPUs in workstations and servers you already own into a private, OpenAI-compatible token service. Company data never leaves company devices.</p><p><img src=\"https://salad.com/img/illus/private-cloud-fleet-wide.svg\" alt=\"An organization's own machines pooled behind a single private endpoint\" />\n<a target=\"_blank\" href=\"https://salad.com/private-cloud\">Learn more →</a></p></div></div></div><div><div><p><span>Optimized per workload</span></p><h2>Every modality, tuned for the network.</h2><p>Published benchmarks, not promises. Each figure links to the methodology.</p></div><div><div><h3>Image generation</h3><p>5,243 Flux.1-Schnell images per dollar. Civitai serves 10 million images a day on 600+ Salad GPUs.</p><p><a target=\"_blank\" href=\"https://salad.com/image-generation\">Image generation →</a></p></div><div><h3>Transcription</h3><p>95.1% accuracy on CommonVoice, the top of the benchmark, from $0.16 per audio hour.</p><p><a target=\"_blank\" href=\"https://salad.com/transcription\">Transcription API →</a></p></div><div><h3>Text-to-speech</h3><p>Up to 6 million words per dollar with OpenVoice on RTX-class GPUs.</p><p><a target=\"_blank\" href=\"https://salad.com/voice-ai\">Voice AI →</a></p></div><div><h3>LLM inference</h3><p>Flat hourly GPUs for agents and RAG, or per-token pricing through AI Gateway from $0.06 per million input tokens.</p><p><a target=\"_blank\" href=\"https://salad.com/ai-gateway\">AI Gateway →</a></p></div><div><h3>Computer vision</h3><p>309,000 images tagged per dollar with RAM++; YOLOv8 object detection for 73% less than Azure.</p><p><a target=\"_blank\" href=\"https://salad.com/computer-vision\">Computer vision →</a></p></div><div><h3>Batch &amp; simulation</h3><p>1,000,000 hours of audio transcribed for $1,260; GROMACS at 90%+ below data-center pricing.</p><p><a target=\"_blank\" href=\"https://salad.com/batch\">Batch processing →</a></p></div></div></div><div><div><p><span>Customer stories</span></p><h2>Teams ship on Salad.</h2></div><div><div><p><span>Civitai</span></p><p>\"By switching to SaladCloud, we are serving inference on over 600 consumer GPUs to deliver 10 Million images per day and training more than 15,000 LoRAs per month. SaladCloud not only had the lowest GPU prices in the market but also offered us incredible scalability.\"</p><p>Justin Maier · Founder &amp; CEO, Civitai<a target=\"_blank\" href=\"https://blog.salad.com/civitai-salad/\">Read the case study →</a></p></div><div><p><span>Blend</span></p><p>\"On SaladCloud's consumer GPUs, we are running 3X more scale at half the cost of A100s on our local provider and almost 85% less cost than the two major hyperscalers we were using before. I'm not losing sleep over scaling issues anymore.\"</p><p>Jamsheed Kamardeen · CTO, Blend<a target=\"_blank\" href=\"https://blog.salad.com/blend-salad/\">Read the case study →</a></p></div><div><p><span>Klyne.ai</span></p><p>\"If you want access to 1000s of GPUs, you can get them on SaladCloud for better cost-efficiency. Salad is also really customer friendly, something you cannot get from a larger cloud provider as a startup.\"</p><p>Zachary Lawrence · CEO, Klyne.ai<a target=\"_blank\" href=\"https://blog.salad.com/klyne-ai/\">Read the case study →</a></p></div></div></div><div><div><p><span>From the blog</span></p><h2>How to build on Salad.</h2><p>Benchmarks, tutorials, and product updates.</p></div><p><a target=\"_blank\" href=\"https://salad.com/resources\">All posts</a></p></div><div><details><summary>What kind of GPUs are on SaladCloud?</summary><p>NVIDIA RTX-class consumer GPUs, from the RTX 3060 through the RTX 5090 (32 GB), plus selected AMD classes. Every GPU is benchmarked before it is admitted and continuously scored by our trust rating. Data-center and workstation GPUs, starting with the RTX PRO 6000 Blackwell, are available on contract through <a target=\"_blank\" href=\"https://salad.com/dedicated\">Salad Dedicated</a>.</p></details><details><summary>How is this different from a spot instance?</summary><p>Community Cloud nodes are interruptible, like spot, and priced by priority tier (High, Medium, Low, Lowest). Unlike spot, Salad Container Engine handles the consequences: it reallocates your workload to another node of the same class automatically, bills only for running time, and never charges for cold start or image download.</p></details><details><summary>How does security work on a network of other people's computers?</summary><p>Your container runs inside a Linux virtual machine partitioned from the host by a hypervisor, with image, configuration, and traffic encrypted in transit and at rest. Host-intrusion detection destroys the environment and blacklists the machine if anything attempts to access it. Salad is SOC 2 Type I compliant. Read the <a target=\"_blank\" href=\"https://salad.com/security\">security overview</a>.</p></details><details><summary>What workloads are not a fit?</summary><p>Anything that needs sub-10-millisecond latency, multi-GPU NVLink training, or data-residency guarantees that a consumer network cannot provide. For those requirements, Salad Dedicated offers reserved hardware and Private Cloud runs on your own infrastructure. Our engineers are available to support the deployment choice and architecture.</p></details><details><summary>Why do people share their GPUs with Salad?</summary><p>They earn. Salad Chefs run our desktop app when their PC is idle and redeem Salad Balance for PayPal, games, gift cards, and more. Since 2018, more than 450,000 GPUs have contributed compute to the network. <a target=\"_blank\" href=\"https://salad.com/download\">Learn about becoming a Chef</a>.</p></details><details><summary>Can we run Salad's technology inside our own company?</summary><p>Yes. <a target=\"_blank\" href=\"https://salad.com/private-cloud\">Private Cloud</a> deploys Salad's orchestration stack on your infrastructure and pools the idle GPUs in your existing workstations and servers into a private, OpenAI-compatible endpoint. Prompts, completions, and embeddings never leave your network.</p></details></div><div><h2>Explore Salad today.</h2><p>Deploy on SaladCloud, or talk to sales about reserved and private options.</p></div></div>",
"author": "",
"favicon": "https://salad.com/img/favicon.svg",
"source": "salad.com",
"published": "",
"ttr": 231,
"type": "website"
}