RentGPU RentGPU
Trouver un GPU →
by DeepSeek

DeepSeek-V3.1.

text open weights 164K ctx
Cheapest input
$0.21/M
on DeepInfra
Cheapest output
$0.79/M
on DeepInfra
Hosted equiv.
~$0.28/hr
@ 100 tok/s on DeepInfra

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.21 $0.79 Launch ↗
Together AI hosted inference $0.6 $1.7 Launch ↗
FAQ

Frequently asked.

How do I run DeepSeek-V3.1?
DeepSeek-V3.1 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-V3.1?
DeepSeek-V3.1 is available via DeepSeek Platform, Together AI, DeepInfra. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run DeepSeek-V3.1?
API pricing starts at $0.21/M input tokens and $0.79/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is DeepSeek-V3.1 open-source or proprietary?
DeepSeek-V3.1 is open-weight under the license. You can download and self-host it.