The cheapest way to try reasoning: the same think-out-loud manner as bigger R1 models, but it fits a single inexpensive card. Good at school and olympiad maths, weaker on general knowledge.
| MATH-500 | 92.8 | |
|---|---|---|
| AIME 2024 | 55.5 | |
| GPQA Diamond | 49.1 |
Which GPU does DeepSeek-R1 7B need?
The entry configuration is 1x V100, which delivers around 28 tokens per second. For more parallel requests and headroom on speed, go with 1x H100.
How much does DeepSeek-R1 7B cost?
An hour of DeepSeek-R1 7B runs from $0.22 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 7B from my code?
Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass deepseek-r1:7b as the model name. Code written against the OpenAI API needs no changes.
Does the data stay private?
Yes. DeepSeek-R1 7B 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 7B have?
DeepSeek-R1 7B holds 32K tokens of context per request and ships under the MIT license, so you can use it commercially on your own hosting terms.