Models

DeepSeek-V4-Pro: GPU memory and hosting cost

Open weights · 1598.84 billion parameters · Mixture of experts · 1,048,576-token context · licence mit

No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.

Run it yourself

It needs 3997.1 GB of GPU memory at fp16, the precision it ships in.

More from DeepSeek

• DeepSeek V3.1
• DeepSeek-V4-Flash-0731
• DeepSeek-V3.2
• DeepSeek-V3-0324
• DeepSeek-V4-Flash
• DeepSeek-R1

Similar size, open weights

• Kimi-K3
• Kimi-K2.6
• Kimi-K2-Instruct
• Kimi-K2-Thinking-NVFP4
• Kimi-K2.7-Code
• Kimi-K2-Instruct-0905

List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.