RentGPU RentGPU
GPU finden →
by DeepSeek

DeepSeek: DeepSeek V3.2.

text open weights 131K ctx
Cheapest input
$0.252/M
on DeepSeek Platform
Cheapest output
$0.378/M
on DeepSeek Platform
Fastest
22 tok/s
on OpenRouter
Hosted equiv.
~$0.14/hr
@ 100 tok/s on DeepSeek Platform

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse att

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepSeek Platform api direct $0.252 $0.378 Launch ↗
OpenRouter api aggregator $0.252 $0.378 Launch ↗
DeepInfra hosted inference $0.26 $0.38 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 22.0 846 ms 4265 ms
FAQ

Frequently asked.

How do I run DeepSeek: DeepSeek V3.2?
DeepSeek: DeepSeek V3.2 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 V3.2?
DeepSeek: DeepSeek V3.2 is available via DeepSeek Platform, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run DeepSeek: DeepSeek V3.2?
API pricing starts at $0.252/M input tokens and $0.378/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is DeepSeek: DeepSeek V3.2 open-source or proprietary?
DeepSeek: DeepSeek V3.2 is open-weight under the license. You can download and self-host it.