RentGPU RentGPU
Find a GPU →
by ~deepseek

DeepSeek V4 Flash Latest.

text closed 1M ctx
Cheapest input
$0.09/M
on OpenRouter
Cheapest output
$0.18/M
on OpenRouter
Hosted equiv.
~$0.06/hr
@ 100 tok/s on OpenRouter

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Hosted API only

No self-host path — closed weights.

DeepSeek V4 Flash Latest's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.09 $0.18 Launch ↗
FAQ

Frequently asked.

How do I run DeepSeek V4 Flash Latest?
DeepSeek V4 Flash Latest is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access DeepSeek V4 Flash Latest?
DeepSeek V4 Flash Latest is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run DeepSeek V4 Flash Latest?
API pricing starts at $0.09/M input tokens and $0.18/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is DeepSeek V4 Flash Latest open-source or proprietary?
DeepSeek V4 Flash Latest is a proprietary model from ~deepseek. Access is API-only — there are no public weights to download.