Skip to content

NVIDIA H200 Rental Price

Cheapest on-demand NVIDIA H200 (141 GB) on 2026-10-10 14:06 UTC: $4.61 per GPU-hour on Vast.ai. Prices from 4 providers, checked every hour.

What can I run on it? Open the calculator →

NVIDIA H200 price history

Loading the daily history…

Which models fit on one NVIDIA H200

With 4-bit weights and an 8K-token context, a single NVIDIA H200 runs: Qwen3.8-Flash-Next, Agnes-3.0-Qwen, Qwen3.5 122B-A10B, Nemotron 3 Super 120B-A12B, gpt-oss 120B, Llama 4 Scout 17B-16E, Qwen3-Coder-Next 80B-A3B, Kolibri-1, Llama 3.3 70B, Ornith 1.5 35B-A3B, Qwen3.6 35B-A3B, Qwen3 32B, Nemotron 3 Nano 30B-A3B, Gemma 4 31B, Qwen3-Coder 30B-A3B, JEV 27B VL, Qwen3.8 27B, Clef, Gemma 4 26B-A4B, Mistral Small 3.2 24B, LFM2 24B-A2B, gpt-oss 20B, Mellum2.1 12B-A2.5B, Gemma 4 12B, Humanizer, Ornith 1.5 9B, Qwen3.5 9B, Clef Flash, LFM2.5 8B-A1B, Llama 3.1 8B, Qwen3.5 4B, LightOnOCR-3 4B, Spark-X2.5 4B, D1 3B.

NVIDIA H200 rental FAQ

How much does it cost to rent an NVIDIA H200?

On 2026-10-10, the cheapest on-demand NVIDIA H200 costs $4.61 per GPU-hour on Vast.ai; across 4 providers prices range from $4.61 to $10.60. An 8-GPU server costs about $36.86 per hour, and one GPU running all month about $3,363.11.

Which cloud is cheapest for the NVIDIA H200?

Vast.ai at $4.61 per hour on 2026-10-10. Marketplace prices (Vast.ai) depend on the host and move within the day; the history on this page shows how they evolve.

Which LLMs can run on a single NVIDIA H200?

With 4-bit weights and an 8K-token context: Qwen3.8-Flash-Next, Agnes-3.0-Qwen, Qwen3.5 122B-A10B, Nemotron 3 Super 120B-A12B, gpt-oss 120B, Llama 4 Scout 17B-16E, Qwen3-Coder-Next 80B-A3B, Kolibri-1, Llama 3.3 70B, Ornith 1.5 35B-A3B, Qwen3.6 35B-A3B, Qwen3 32B, Nemotron 3 Nano 30B-A3B, Gemma 4 31B, Qwen3-Coder 30B-A3B, JEV 27B VL, Qwen3.8 27B, Clef, Gemma 4 26B-A4B, Mistral Small 3.2 24B, LFM2 24B-A2B, gpt-oss 20B, Mellum2.1 12B-A2.5B, Gemma 4 12B, Humanizer, Ornith 1.5 9B, Qwen3.5 9B, Clef Flash, LFM2.5 8B-A1B, Llama 3.1 8B, Qwen3.5 4B, LightOnOCR-3 4B, Spark-X2.5 4B, D1 3B. Larger models need several GPUs; the LLM VRAM calculator sizes them.