Pricing Pages and Price Feed
GPU prices on Lium are public. No account or key needed.
| Surface | URL | For |
|---|---|---|
| Pricing hub: every GPU model with its live price range | https://lium.io/pricing | people, search engines, agents |
| One page per GPU model | https://lium.io/gpu/<slug>, e.g. /gpu/h100, /gpu/h200 | the same, per model |
| Price feed, JSON | https://lium.io/pricing.json | aggregators, comparison sites, agents |
| Price feed, CSV | https://lium.io/pricing.csv (Price Feed CSV) | spreadsheets, data warehouses |
All three use the same data and are cached for up to an hour. Per-node rows are in the Public Nodes Feed.
/pricing.json
curl -sSL https://lium.io/pricing.json
{
"generated_at": "2026-09-07T09:32:29.120Z",
"age_budget_seconds": 900,
"stale": false,
"unit": "USD per GPU-hour",
"nodes_url": "https://lium.io/api/public/v1/nodes",
"count": 91,
"fleet": {
"generated_at": "2026-09-07T09:32:29.120Z",
"listed_gpus": 1480,
"rented_gpus": 1234,
"idle_gpus": 246,
"available_gpus": 209,
"available_nodes": 98
},
"models": [
{
"model": "NVIDIA H100 80GB HBM3",
"gpu_model": "H100 80GB HBM3",
"name": "H100 80GB HBM3",
"slug": "h100-80gb-hbm3",
"url": "https://lium.io/gpu/h100",
"gpu_class": "datacenter",
"reference_price_usd_per_gpu_hour": 1.49,
"min_price_usd_per_gpu_hour": 1.2,
"max_price_usd_per_gpu_hour": 2.75,
"available_nodes": 20,
"available_gpus": 56,
"vram_gb": 80,
"architecture": "hopper",
"browse_url": "https://lium.io/?gpu=NVIDIA%20H100%2080GB%20HBM3",
"updated_at": "2026-09-07T09:32:29.120Z",
"listed_gpus": 120,
"rented_gpus": 98,
"idle_gpus": 22
}
]
}
| Field | Meaning |
|---|---|
generated_at | When the prices were read |
age_budget_seconds | 900: after this age, availability is not confirmed |
stale | true when generated_at is older than age_budget_seconds (last good numbers while the backend is down) |
unit | Always USD per GPU-hour |
nodes_url | The Public Nodes Feed |
fleet | Marketplace totals: listed, rented, idle and available GPUs |
models[].model | Full machine name |
models[].gpu_model | Join key with the nodes feed's gpu_model |
models[].slug, url | The model's page |
models[].gpu_class | datacenter, professional or consumer |
models[].reference_price_usd_per_gpu_hour | Lium's reference price for the model |
models[].min_price_usd_per_gpu_hour, max_price_usd_per_gpu_hour | Cheapest and dearest live price now |
models[].available_nodes, available_gpus | Rentable now |
models[].browse_url | Rent-now link on lium.io |
Fields are only ever added, never renamed or removed.
/pricing and /gpu/<slug>
The hub lists every model with its price range and links to its page. <slug> is models[].slug from the feed. Short names redirect to the main model page, for example /gpu/a100 → /gpu/a100-sxm4-80gb. Link the feed's url to skip the redirect. Each page shows when its prices were read ("as of HH:MM UTC"); after 15 minutes it says availability is not confirmed.
Markdown for agents
/, /pricing and every /gpu/<slug> page answer in markdown with Accept: text/markdown:
curl -sSL -H 'Accept: text/markdown' https://lium.io/pricing
curl -sSL -H 'Accept: text/markdown' https://lium.io/gpu/h200
# Lium: GPU rental marketplace
...
## Prices right now
### Data center
| GPU | $ / GPU / hour | Rentable now |
| --- | --- | --- |
| [B200](https://lium.io/?gpu=NVIDIA%20B200) | $5.50 – $6.53 | 5 pods · 19 GPUs |
| [H200](https://lium.io/?gpu=NVIDIA%20H200) | $2.75 – $4.23 | 10 pods · 29 GPUs |
https://lium.io/llms.txt has the same fleet totals as plain text.