Skip to content
mcp/harbor

Lium GPU Cloud changelog

io.github.datura-ai/lium

23 changes recorded. MCP Harbor re-reads this listing from the official registry every six hours and asks the live server what it exposes, and keeps what changed between one look and the next.

  • server.json 1 field changed
    version
    0.42.0 0.45.1

  • server.json 1 field changed
    version
    0.41.12 0.42.0
  • server.json 1 field changed
    version
    0.41.11 0.41.12
  • server.json 1 field changed
    version
    0.41.10 0.41.11

  • server.json 1 field changed
    version
    0.41.8 0.41.10

  • server.json 1 field changed
    version
    0.41.7 0.41.8

  • server.json 1 field changed
    version
    0.41.4 0.41.7
  • llms.txt +33 −26

    https://lium.io/llms.txt 

    − Live fleet totals (read 2026-10-27T19:20:35.949Z; JSON: https://lium.io/pricing.json, "fleet" and per-model listed_gpus / rented_gpus / idle_gpus):− - GPUs listed: 1,867; rented: 1,613 (86%); idle: 254− - Free GPUs on nodes rentable right now: 267 across 81 nodes (https://lium.io/api/public/v1/nodes)−   B300 SXM6: 483 / 404 / 79−   RTX 5090: 289 / 269 / 20−   H200: 222 / 168 / 54−   H100 80GB HBM3: 146 / 124 / 22−   RTX 4090: 121 / 121 / 0−   RTX 3090: 95 / 90 / 5−   B200: 83 / 54 / 29−   RTX PRO 6000 Blackwell Server Edition: 81 / 81 / 0−   RTX A6000: 79 / 68 / 11−   L40S: 71 / 71 / 0−   RTX 6000 Ada Generation: 41 / 36 / 5−   A100-SXM4-80GB: 38 / 38 / 0−   L40: 27 / 27 / 0−   RTX PRO 6000 Blackwell Workstation Edition: 27 / 27 / 0−   RTX A4000: 14 / 6 / 8−   H200 NVL: 10 / 7 / 3−   Tesla V100: 10 / 0 / 10−   RTX 5070 Ti: 5 / 1 / 4−   RTX 5060 Ti: 4 / 1 / 3−   H100 PCIe: 3 / 3 / 0−   RTX A5000: 2 / 2 / 0−   RTX 5080: 1 / 0 / 1−   RTX PRO 5000 Blackwell: 1 / 1 / 0+ Live fleet totals (read 2026-11-06T07:38:23.191Z; JSON: https://lium.io/pricing.json, "fleet" and per-model listed_gpus / rented_gpus / idle_gpus):+ - GPUs listed: 1,908; rented: 1,497 (78%); idle: 411+ - Free GPUs on nodes rentable right now: 395 across 134 nodes (https://lium.io/api/public/v1/nodes)+   RTX 5090: 457 / 431 / 26+   B300 SXM6: 338 / 314 / 24+   H200: 165 / 133 / 32+   RTX 4090: 119 / 64 / 55+   RTX PRO 6000 Blackwell Server Edition: 117 / 77 / 40+   H100 80GB HBM3: 116 / 67 / 49+   RTX 3090: 107 / 87 / 20+   B200: 103 / 61 / 42+   RTX A6000: 81 / 46 / 35+   L40S: 67 / 43 / 24+   A100-SXM4-80GB: 54 / 54 / 0+   RTX 6000 Ada Generation: 41 / 18 / 23+   RTX PRO 6000 Blackwell Workstation Edition: 30 / 22 / 8+   L40: 27 / 23 / 4+   RTX 5070 Ti: 15 / 3 / 12+   H100 PCIe: 13 / 12 / 1+   RTX A4000: 8 / 0 / 8+   H200 NVL: 6 / 4 / 2+   RTX 5060 Ti: 6 / 6 / 0+   RTX 5080: 6 / 5 / 1+   RTX PRO 4000 Blackwell: 4 / 0 / 4+   RTX 4070 Ti SUPER: 3 / 3 / 0+   CMP 170HX: 2 / 2 / 0+   RTX PRO 5000 Blackwell: 2 / 1 / 1+   T4: 2 / 2 / 0+   RTX 3060: 1 / 1 / 0+   RTX 3080: 1 / 1 / 0+   RTX 3080 Ti: 1 / 1 / 0+   RTX PRO 4500 Blackwell Server Edition: 1 / 1 / 0+   RTX PRO 6000 Blackwell Max-Q Workstation Edition: 1 / 1 / 0

  • server.json 1 field changed
    version
    0.41.3 0.41.4

  • server.json 1 field changed
    version
    0.35.1 0.41.3

  • server.json 1 field changed
    version
    0.34.2 0.35.1

  • server.json 1 field changed
    version
    0.34.0 0.34.2

  • server.json 1 field changed
    version
    0.33.0 0.34.0
  • llms.txt +31 −25

    https://lium.io/llms.txt 

    − Live fleet totals (read 2026-10-20T18:42:54.764Z; JSON: https://lium.io/pricing.json, "fleet" and per-model listed_gpus / rented_gpus / idle_gpus):− - GPUs listed: 1,765; rented: 1,566 (89%); idle: 199− - Free GPUs on nodes rentable right now: 228 across 66 nodes (https://lium.io/api/public/v1/nodes)−   H100 80GB HBM3: 268 / 212 / 56−   RTX 5090: 259 / 252 / 7−   B300 SXM6: 226 / 189 / 37−   RTX PRO 6000 Blackwell Server Edition: 206 / 182 / 24−   H200: 171 / 165 / 6−   RTX 3090: 103 / 103 / 0−   RTX 4090: 100 / 87 / 13−   RTX A6000: 77 / 70 / 7−   B200: 76 / 65 / 11−   L40S: 69 / 69 / 0−   A100-SXM4-80GB: 62 / 45 / 17−   RTX 6000 Ada Generation: 50 / 38 / 12−   L40: 27 / 26 / 1−   RTX PRO 6000 Blackwell Workstation Edition: 19 / 19 / 0−   H100 PCIe: 8 / 8 / 0−   RTX 5060 Ti: 7 / 1 / 6−   H200 NVL: 6 / 6 / 0−   RTX A4000: 6 / 6 / 0−   RTX 5070 Ti: 4 / 2 / 2−   CMP 170HX: 2 / 2 / 0−   RTX 3060: 2 / 2 / 0−   RTX 3080: 1 / 1 / 0+ > Docs cover lium CLI and SDK 0.16.1 (released 2026-10-14); last updated 2026-10-15.+ Live fleet totals (read 2026-10-27T19:20:35.949Z; JSON: https://lium.io/pricing.json, "fleet" and per-model listed_gpus / rented_gpus / idle_gpus):+ - GPUs listed: 1,867; rented: 1,613 (86%); idle: 254+ - Free GPUs on nodes rentable right now: 267 across 81 nodes (https://lium.io/api/public/v1/nodes)+   B300 SXM6: 483 / 404 / 79+   RTX 5090: 289 / 269 / 20+   H200: 222 / 168 / 54+   H100 80GB HBM3: 146 / 124 / 22+   RTX 4090: 121 / 121 / 0+   RTX 3090: 95 / 90 / 5+   B200: 83 / 54 / 29+   RTX PRO 6000 Blackwell Server Edition: 81 / 81 / 0+   RTX A6000: 79 / 68 / 11+   L40S: 71 / 71 / 0+   RTX 6000 Ada Generation: 41 / 36 / 5+   A100-SXM4-80GB: 38 / 38 / 0+   L40: 27 / 27 / 0+   RTX PRO 6000 Blackwell Workstation Edition: 27 / 27 / 0+   RTX A4000: 14 / 6 / 8+   H200 NVL: 10 / 7 / 3+   Tesla V100: 10 / 0 / 10+   RTX 5070 Ti: 5 / 1 / 4+   RTX 5060 Ti: 4 / 1 / 3+   H100 PCIe: 3 / 3 / 0+   RTX 5080: 1 / 0 / 1+   RTX PRO 5000 Blackwell: 1 / 1 / 0+ Answer pages (server-rendered with live numbers, no account):+ - Rent out your GPU: what an RTX 4090, RTX 5090 or H100 earns per month, requirements, payouts, steps: https://lium.io/rent-out-your-gpu+ - Provider earnings per GPU model, last 30 days (JSON): https://provider-api.lium.io/public/provider-economics+ - Cheapest H100 by the hour (live lowest ask, billed per second): https://lium.io/gpu/h100+ - Cheapest RTX 4090, RTX 5090 and A100 80GB by the hour: https://lium.io/gpu/rtx-4090 , https://lium.io/gpu/rtx-5090 , https://lium.io/gpu/a100-sxm4-80gb
  • server.json 1 field changed
    version
    0.30.1 0.33.0

  • server.json 1 field changed
    version
    0.29.1 0.30.1
  • server.json 1 field changed
    version
    0.28.3 0.29.1
  • server.json 1 field changed
    version
    0.28.2 0.28.3

  • server.json 1 field changed
    version
    0.28.1 0.28.2
  • server.json 1 field changed
    version
    0.28.0 0.28.1

  • server.json 1 field changed
    version
    0.27.2 0.28.0
  • server.json 1 field changed
    version
    0.26.0 0.27.2

  • server.json 1 field changed
    version
    0.25.0 0.26.0
Lium GPU Cloud MCP server