R1

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!

ChatDeepSeek64k tokens$0.763 / $2.7251 · 1M

deepseek/deepseek-r1

Context
64k tokens
Completion cap
16,000
Tools
Yes
JSON
Yes
Released
2025-01-20

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-r1",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is R1?
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely! R1 runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-r1.
Is R1 free?
No. Input is $0.763 per 1M tokens and output is $2.7251 per 1M tokens on Geek Hub (markup included).
What is the context length of R1?
R1 has a 64k tokens context window. It supports up to 16,000 completion tokens.
Does R1 support tool calling and structured outputs?
R1 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was R1 released?
R1 was released on 2025-01-20.

More models from DeepSeek