DeepSeek: R1 Distill Llama 70B
deepseek/deepseek-r1-distill-llama-70b
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
Modalities
Text
In / out price
₩1,404 / ₩1,404
1M
Context
8K
Released
Jan 24, 2025
FAQ
Frequently asked questions
How do I call this model?
Send a request to `/api/v1/chat/completions` with `model` set to this model ID. Changing the base_url of the OpenAI SDK is enough.
How is the price calculated?
The upstream cost in USD is multiplied by the exchange rate and the margin to produce a won price. The cost of each request is recorded in the response headers and in your activity log.
Does this run on a local GPU?
If a local GPU serves this model, it goes first. When there is no local slot or it fails, the request falls through to an external provider.
Are my conversations stored?
API request bodies are never stored. Only conversations from the Chat screen are saved, and you can turn that off in settings.