vast.ai (@vast

vast.ai

733 posts

vast.ai

@vast_ai

Vast is the infrastructure layer where AI agents autonomously design, procure, and optimize their own compute.

California, USA

Joined August 2018

Pinned
vast.ai
@vast_ai
Apr 24
Search. Provision. Scale. Three lines of Python. pip install vastai from vastai_sdk import VastAI vast = VastAI(api_key="YOUR_API_KEY") offers = vast.search_offers(query="gpu_name=H100 num_gpus>=4") instance = vast.launch_instance(num_gpus="4", gpu_name="H100",
33K
vast.ai
@vast_ai
21m
people keep saying h100s are holding steady but they dropped 8% this week. $2.15 median, $1.87 at p10. Supply is tight at 59 cards though
145
vast.ai
@vast_ai
Jun 19
rtx 5090 at $0.50/hr median with 1,244 available. Prices down 6% from last week.
1.8K
vast.ai
@vast_ai
Jun 18
deepseek v3 on 8xH200, $3.42/hr. 211 instances available right now across the fleet
1.7K
vast.ai
@vast_ai
Jun 17
We built a fully functional coding agent in under 100 lines of Python. No framework. No magic. Just the model requesting actions and your program executing them. Runs on a single RTX 5090 with Ollama. Full code + breakdown:
How to Build an Agent on Vast.ai in Less Than 100 Lines of Python
From vast.ai
1.4K
vast.ai
@vast_ai
Jun 17
A100 80GB median is $1.05/hr, bottom decile hits $0.67/hr. 141 cards live. Solid option if you're doing multi-GPU training runs on a budget.
1.1K
vast.ai
@vast_ai
Jun 16
NEW Installer Wizard for Hosts This TUI offers a new guided terminal setup that replaces the CLI script. It walks you through each step, validates your driver, hardware, ports, and speed before installing, and gives plain-English fixes instead of stack traces. Find the guided
GIF
956
vast.ai
@vast_ai
Jun 16
B300 has 2x the memory of H200 (288 GB vs 141 GB) and 8 TB/s bandwidth. But is it actually worth the 1,400W TGP for your workload? We break down H200 vs B300: specs, use cases, and when Blackwell Ultra is the right call 🧵
NVIDIA B300 vs. H200: Is Blackwell Ultra Worth the Upgrade?
From vast.ai
822
vast.ai
@vast_ai
Jun 13
running flux.1 today, 12B fits clean on a single 4090. $0.44/hr with 1475 units up across the fleet.
1.6K
vast.ai
@vast_ai
Jun 11
June Product Update NVIDIA B300 GPUs are now available on Vast.ai, alongside hundreds of new B200s. This month's updates also include: • Revamped serverless metrics • Improved serverless UI performance • New Qwen3.6 and Gemma 4 templates • TurboQuant support
Rent GPUs | Vast.ai
From vast.ai
2K
vast.ai
@vast_ai
Jun 11
B200s dropped 27% in a week, now $4.38/hr median. 252 available. New supply is landing fast on these.
1.2K
vast.ai
@vast_ai
Jun 6
The NVIDIA B300 has 288 GB of HBM3e memory. That's 50% more than the B200, 2x the H200, and 3.6x the H100. A single GPU can fit a full 70B model in FP16 with room left for KV cache. No quantization.
Everything You Need to Know About the NVIDIA Blackwell Ultra B300
From vast.ai
2.9K
vast.ai
@vast_ai
Jun 6
5090s at $0.67/hr if you catch the p10. 32GB GDDR7 is enough for most LoRA jobs without offloading anything
1.5K