by DeepSeek

DeepSeek V4 Pro.

text open weights datacenter 1602B params 1M ctx
Cheapest input
$0.66/M
on DeepSeek Platform
Cheapest output
$1.5/M
on OpenRouter
Smallest GPU
4× AMD MI325
$12.38/hr
Description

About DeepSeek V4 Pro.

The larger model in the DeepSeek-V4 preview pair, a Mixture-of-Experts language model with 1.6T total parameters and 49B active per token. It supports a one million token context and uses a hybrid attention design that DeepSeek says needs about a quarter of the per-token compute and a tenth of the cache of its V3.2 predecessor at that length. It offers a maximum reasoning effort mode and is released under the MIT licence.

Context window

How much it can remember.

1M tokens ≈ 786,432 English words
4K 32K 128K 1M
Capabilities

What it can do.

· Vision input
· Audio input
· Video input
· Function calling
· Tool use
· JSON mode
✓ Streaming
· Fine-tuning