A model that thinks first and answers second: it unrolls a chain of reasoning and therefore solves tasks where others slide into plausible nonsense. The trade-off is latency, so it is for hard analysis rather than real-time chat.
| MATH-500 | 94.3 | |
|---|---|---|
| AIME 2024 | 72.6 | |
| GPQA Diamond | 62.1 |
Which GPU does DeepSeek-R1 32B need?
The entry configuration is 1x RTX5090, which delivers around 32 tokens per second. For more parallel requests and headroom on speed, go with 1x H100.
How much does DeepSeek-R1 32B cost?
An hour of DeepSeek-R1 32B runs from $0.65 to $3.33 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.
How do I call DeepSeek-R1 32B from my code?
Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass deepseek-r1:32b as the model name. Code written against the OpenAI API needs no changes.
Does the data stay private?
Yes. DeepSeek-R1 32B runs on a dedicated GPU server inside a private loop: requests and responses never reach the model vendor and are not used for training.
What context window and license does DeepSeek-R1 32B have?
DeepSeek-R1 32B holds 32K tokens of context per request and ships under the MIT license, so you can use it commercially on your own hosting terms.