Use-case guide · Reasoning / agentic

Should you pick H200 SXM for reasoning / agentic?

H200 SXM has 141 GB VRAM. Whether it's the right fit for reasoning / agentic depends on your model size, expected QPS, and budget. Below is what we're seeing in production.

VRAM + model fit

H200 SXM fits models up to ~99B parameters in BF16 comfortably with room for KV-cache. For reasoning / agentic specifically, you'll want to leave headroom for context length growth.

Pricing

Live pricing across all providers for H200 SXM is on the GPU detail page — click through for the sortable list.

Throughput

On reasoning / agentic workloads, H200 SXM typically delivers the throughput published in its FP16 spec, minus the framework overhead (vLLM ≈ 85% MFU, TGI ≈ 70%).

Try the calculator to size the hardware for your specific model, or see all GPUs on the InferenceScore leaderboard.