Price floor Every GPU at least 30% below the market median — re-checked against the marketplace weekly.

See the proof

Use case · LLM inference

LLM inference GPUs: tokens priced like a utility bill

Fixed GPU prices turn $/token into arithmetic: pick the smallest card that holds your model + KV-cache, saturate it with vLLM continuous batching, divide. A RTX 5090 at $0.318/hr serves a 8B model for pennies per million tokens.

The serving cards, by model size

VRAM decides; price-per-VRAM ranks the candidates.

TierGPUVRAMOn-demandInterruptibleWhy this cardAction
GoodRTX 509032 GB$0.318$0.15932 GB GDDR7 — the $/token king for 7B–14B FP16 and 32B 4-bit chat models.Deploy
BetterL40S48 GB$0.466$0.23348 GB and server-grade cooling for 24/7 endpoints; 32B class and long-context 14B.Deploy
BestH100 PCIE80 GB$2.147$1.07380 GB HBM3 for 70B quantized on one card — or FP8 for maximum throughput per dollar.Deploy

Bigger than 70B? Tensor-parallel across 2–8× cards on one machine — the per-GPU price never changes. Sizing tables: VRAM guide.

$/million tokens, computed honestly

Throughput varies with context and batch mix, so we publish the formula, not a marketing number:

$/M tokens = GPU $/hr ÷ (tokens/s × 3600) × 1,000,000

A RTX 5090 at $0.318/hr sustaining ~2,800 tok/s of Llama-3.1-8B under continuous batching → $0.032/M tokens. The same card interruptible halves it.

Benchmark your own model in 10 minutes — the serving guide ships the exact vllm bench command.

Serving patterns

  • Reserved + vLLM for the baseline load — −35% on the card that never sleeps.
  • Serverless burst on top — scale-to-zero workers absorb the spikes.
  • Model library volume mounted read-only — new workers skip the 40 GB download.
  • Quantize first — AWQ/GPTQ 4-bit doubles the models a card can hold, rarely hurts chat quality.

Templates: vLLM, Ollama, TGWUI — all OpenAI-compatible out of the box.

LLM inference GPUs: FAQ

What is the cheapest way to serve a 7B–14B model?

A single RTX 5090 at $0.318/hr running vLLM. At typical chat throughput that lands well under $0.15 per million output tokens — an order of magnitude below API-provider pricing for comparable open models.

When do I need an 80 GB card?

Roughly at 70B: a 4-bit 70B needs ~44 GB plus KV-cache, so a single H100 PCIE (80 GB) or 2× L40S with tensor parallelism. FP16 70B wants 2× 80 GB. Below 32B, 32–48 GB cards are the value zone.

Instances or serverless for serving?

Steady saturating traffic → a reserved instance (−35%) you keep hot. Spiky or overnight-idle traffic → serverless with scale-to-zero. Same per-second prices; the difference is who pays for idle.

Deploy your first GPU in under a minute

Top up in crypto, benchmark us against your current provider. Per-second billing, fixed prices ≥ 30% below market — cancel by just stopping the instance.