by DeepSeek

DeepSeek: DeepSeek V3 0324.

text open weights datacenter 689B params 164K ctx
Cheapest input
$0.2/M
on DeepSeek Platform
Cheapest output
$0.77/M
on DeepSeek Platform
Smallest GPU
2× AMD MI325
$5.97/hr

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs real

Smallest GPU to run it See all quantisations →

2× AMD MI325 · $5.97/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepSeek Platform api direct $0.2 $0.77 Launch ↗
OpenRouter api aggregator $0.29 $1.14 Launch ↗
Sources

Official references.

FAQ

Frequently asked.

How do I run DeepSeek: DeepSeek V3 0324?
DeepSeek: DeepSeek V3 0324 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access DeepSeek: DeepSeek V3 0324?
DeepSeek: DeepSeek V3 0324 is available via DeepSeek Platform, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run DeepSeek: DeepSeek V3 0324?
API pricing starts at $0.2/M input tokens and $0.77/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is DeepSeek: DeepSeek V3 0324 open-source or proprietary?
DeepSeek: DeepSeek V3 0324 is open-weight under the license. You can download and self-host it.