Vast.ai
Hacker ApprovedRanked 2 of 6 GPU clouds by recommenders
Rent GPUs by the hour from many hosts, often far cheaper than buying hardware, for training or testing models. Prices vary with demand.
Rent GPUs by the hour from many hosts, often far cheaper than buying hardware, for training or testing models. Prices vary with demand.
38 people gave an opinion
- recommend it
- 37
- criticize it
- 1
- approval share
- 97%
Recommended in 9 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 37 people recommend itNeeds 10 or more, met.
- 37 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Wide choice of GPUs on demand
“A benefit is that if I need a burst of more power, that’s not an issue since it’s available from other hosts.”
Comment from 1 Oct 2026 in “GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price” “rent a vast.ai box with similar specs for a month or two to get a feel for it”
Comment from 17 Oct 2026 in “Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware” “where you can get all kinds of machines on tap for ~$0.20/hour+”
Comment from 3 Aug 2026 in “OpenAI's super PAC is funding AI-generated news site attacking industry critics” - Comment from 3 Sep 2026 in “Show HN: The cheapest GPU cloud – H100s at $2.04/HR, H200s at $3/HR”
- Comment from 23 Aug 2026 in “Why your local LLM feels dumber than it is”
- Comment from 14 May 2026 in “MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble”
- Comment from 4 Oct 2026 in “Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s”
Much cheaper than buying hardware
“Paying runpod or vast or just about anyone else is _far_ cheaper than buying this hardware myself.”
Comment from 8 Jan 2026 in “AWS raises GPU prices 15% on a Saturday, hopes you weren't paying attention” “set one up on vast.ai really quickly and ran it for a day for the price of lunch”
Comment from 11 Mar 2026 in “Show HN: Autoresearch@home” “p2p GPU rental marketplaces like vast.ai can offer much more economical options”
Comment from 20 Jun 2026 in “Ask HN: What technique do you use to make Claude Code deterministic?” - Comment from 3 Aug 2026 in “OpenAI's super PAC is funding AI-generated news site attacking industry critics”
- Comment from 26 Aug 2026 in “GLM-5.3-Flash”
Worked well in practice
“running this model on a B6000 from Vast with a native NVFP4 model weight from Nvidia, it's really good”
Comment from 2 Apr 2026 in “Google releases Gemma 4 open models” “set one up on vast.ai really quickly and ran it for a day for the price of lunch”
Comment from 11 Mar 2026 in “Show HN: Autoresearch@home” “In my limited test it worked quite well, but I only needed it for a few hours.”
Comment from 20 Jul 2026 in “Ask HN: Would you rent M3 Ultra from me?” - Comment from 27 Sep 2026 in “Ember-1”
- Comment from 4 Oct 2026 in “Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s”
- Comment from 20 Jan 2026 in “Majority of CEOs report zero payoff from AI splurge”
Good for training and experiments
“I keep a $10 rolling budget on vast.ai. I tend to use it more for training things, but equally as useful.”
Comment from 28 Oct 2026 in “New 14‑inch MacBook Pro with M6” “I ended up renting GPUs through vast.ai and running the model myself”
Comment from 12 Sep 2026 in “So you want to use OpenRouter?” “Test LLMs on rented GPUs on vast.ai or other similar services”
Comment from 27 Jun 2026 in “Ask HN: MacBook vs. Dedicated GPU for LLM” - Comment from 15 Jun 2026 in “I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models”
- Comment from 23 May 2026 in “Show HN: I Dedicated 4 Years to Mastering Offline Password Cracking”
- Comment from 15 May 2026 in “Welcome to the Strip Mining Era of OSS Security”
- Comment from 11 Jul 2026 in “AI 2040 and the Cult of Intelligence”
Other GPU clouds people recommend
The four most recommended other GPU clouds, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Modal | 38 | 12 | 76% | 11 | — | Approved |
| Vast.aiThis page | 37 | 1 | 97% | 9 | — | Approved |
| RunPod | 28 | 5 | 85% | 11 | — | Approved |
| Verda GPU cloud | 10 | 1 | 91% | 4 | — | Approved |
| Lambda GPU Cloud | 9 | 2 | 82% | 5 | — | — |
What people said
35 of the 40 comments that mention it, newest first. Each links to the original comment.
“I keep a $10 rolling budget on vast.ai. I tend to use it more for training things, but equally as useful.”
“rent a vast.ai box with similar specs for a month or two to get a feel for it”
“Vast worked well for renting 5090s”
“A benefit is that if I need a burst of more power, that’s not an issue since it’s available from other hosts.”
“near 100% utilization on vast.ai at $1 to $1.25 depending on demand”
“Worked pretty well without risking bankruptcy.”
“rent GPUs from companies like Runpod or Vast.ai and serve some very sizable models to yourself”
“I ended up renting GPUs through vast.ai and running the model myself”
“vast.ai has H100 at 1.93/h, H200 at 3.8/h but no 2500$ minimum”
“is a good bet if you need something on demand and are willing to compromise on quality”
“Much faster and cheap as hell, to be honest.”
“pretty wild the variety of prices/hardware that they have”
“there's a better middle ground with renting a GPU VPS off Runpod or Vast or something”
“Why not rent those out on vast.ai and make a little money each month?”
“where you can get all kinds of machines on tap for ~$0.20/hour+”
“In my limited test it worked quite well, but I only needed it for a few hours.”
“tuned up GLM-5.2 on vast.ai or RunPods”
“go rent a B200 on vast.ai for 4 bucks an hour or thereabouts”
“Test LLMs on rented GPUs on vast.ai or other similar services”
“p2p GPU rental marketplaces like vast.ai can offer much more economical options”
“let it run it finish in just a few hours for like ten bucks”
“in the early phases I don't need anything more than a 4090 on Vast.ai”
“I don't need anything more than a 4090 on Vast.ai”
“Rent a gpu from vast.ai or similar an let hashcat have fun”
“The prices are all over the place.”
“hiring a beefy GPU instance at Vast.ai or similar places”
“Need more compute? Rent a machine on vast.ai.”
“I would strongly recommend exploring that option”
“Good to see they're thriving!”
“running this model on a B6000 from Vast with a native NVFP4 model weight from Nvidia, it's really good”
“set one up on vast.ai really quickly and ran it for a day for the price of lunch”
“I found a higher vCPU instance on Vast.ai which hit 700ms”
“I'm very happy with the results.”
“Paying runpod or vast or just about anyone else is _far_ cheaper than buying this hardware myself.”
“But they hit a different hard limit: The VRAM Wall.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.