B200 vs H200 SXM

Open Advisor →

Side-by-side GPU comparison: specs, memory, compute performance, and live cloud pricing.

Verdict

B200 has 51 GB more VRAM, making it better suited for large models and long context windows. For compute-bound workloads like training, B200 delivers 2.3× higher FP16 throughput. At $2.35/hr vs $5.49/hr, H200 SXM is the more cost-efficient choice for inference. B200 supports a broader range of models (659 vs 657 from this catalog), giving more flexibility.

Specifications

B200H200 SXM
VRAM192 GB141 GB
VRAM TypeHBM3eHBM3e
Memory Bandwidth8.0 TB/s4.8 TB/s
FP16 Performance2250 TFLOPS990 TFLOPS
ManufacturerNVIDIANVIDIA
FP8 SupportYesYes
FP4 SupportYesNo

Price / Performance

Based on cheapest single-GPU on-demand pricing. Lower $/TFLOP = better compute value; lower $/GB = better memory value.

B200H200 SXM
$/hr (cheapest)$5.49$2.35✓ best
$/TFLOP (compute value)$0.0024$0.0024✓ best
$/GB VRAM (memory value)$0.0286$0.0167✓ best

Cloud Pricing

Cheapest on-demand price per provider (single GPU).

B200

ProviderOn-demandSpotRent
RunPod$5.49/hr$3.59/hrRent
Nebius$5.50/hr$2.90/hr
Lambda$6.99/hr

H200 SXM

ProviderOn-demandSpotRent
Vast.ai$2.35/hrRent
Nebius$3.50/hr$1.45/hr

Model Compatibility

Models from the catalog that fit on each GPU, grouped by required precision.

B200 (659 models)

H200 SXM (657 models)

You might also compare…

Pricing data refreshed hourly · Last updated April 11, 2026 · Browse all comparisons