DeepSeek R1 is an open-source reasoning model from DeepSeek AI. It demonstrates step-by-step chain-of-thought thinking and rivals GPT-4 on complex reasoning benchmarks. Available in 8B, 14B, 32B, 70B, and 671B MoE variants to match any budget.
Deploy DeepSeek R1 in minutes
Starting at $0.51/hr on dedicated GPU
| Model | GPU | VRAM | Price | Action |
|---|---|---|---|---|
DeepSeek R1 8B Small (8B) | L4 | 24 GB | $0.51/hr | Deploy |
DeepSeek R1 14B Medium (14B, Recommended) | L4 | 24 GB | $0.51/hr | Deploy |
DeepSeek R1 32B Medium+ (32B) | RTX A6000 | 48 GB | $0.64/hr | Deploy |
DeepSeek R1 70B Large (70B) | RTX A6000 | 48 GB | $0.64/hr | Deploy |
DeepSeek V3.1 671B Full (671B MoE) | A100 80GB PCIe | 80 GB | $1.81/hr | Deploy |
Prices include 30% service fee. Billed per minute while running.
Pick your GPU and have it running in minutes. No infrastructure setup required.