Cheap GPUS

Compare live GPU rental and LLM inference prices from inside Claude. Cheap GPUs (cheap-gpus.com) tracks on-demand and spot rental rates from 30+ GPU cloud providers, including vast.ai, RunPod, Lambda, CoreWeave, AWS, Azure and Google Cloud, and per-token prices from 24 LLM inference providers. Prices refresh every few hours. What you can ask: - Cheapest GPU rentals: the lowest current price per GPU-hour for any of 24 GPU families (H100, H200, B200, B300, A100, RTX 5090, L40S and more), on-demand or spot, one row per provider. - GPU price history: daily median prices for a GPU family over the last 90 days. - GPU price forecasts: where prediction markets (Kalshi, Polymarket) and ICE futures expect H100, H200, B200, A100 and RTX 5090 rental prices to go, alongside today's compute-index benchmarks. - Cheapest LLM providers: the lowest-cost providers for a model, with an estimated cost for your input and output token counts. - GPUs needed to host a model: how many of each GPU an open-weight model needs at a given quantization (FP16 to 1-bit), and the cheapest way to rent that setup right now. Example prompts: "What's the cheapest H100 right now?", "How much would 10M input tokens of DeepSeek V3 cost across providers?", "What GPUs do I need to run gpt-oss-120b at 4-bit, and what does it cost per hour?" Read-only public data, no account or sign-in needed. Each result shows when it was last updated, flags stale prices, and links to the matching page on cheap-gpus.com.