RentGPU RentGPU
Find a GPU →
by DeepSeek

DeepSeek: DeepSeek V4 Pro 0813.

text open weights 1M ctx
Cheapest input
$0.5795/M
on OpenRouter
Cheapest output
$1.7384/M
on OpenRouter
Hosted equiv.
~$0.63/hr
@ 100 tok/s on OpenRouter

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.5795 $1.7384 Launch ↗
DeepInfra hosted inference $1.3 $2.6 Launch ↗
Together AI hosted inference $1.32 $3.96 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run DeepSeek: DeepSeek V4 Pro 0813?
DeepSeek: DeepSeek V4 Pro 0813 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 V4 Pro 0813?
DeepSeek: DeepSeek V4 Pro 0813 is available via Fireworks AI, Together AI, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run DeepSeek: DeepSeek V4 Pro 0813?
API pricing starts at $0.435/M input tokens and $0.87/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is DeepSeek: DeepSeek V4 Pro 0813 open-source or proprietary?
DeepSeek: DeepSeek V4 Pro 0813 is open-weight under the license. You can download and self-host it.