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!
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 keyFrequently 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
DeepSeek V4 FlashV4 Flash open-weight, aggressive pricing with 1M context. Cache hit drops input to $0.0028. Replaces DeepSeek Chat V3.
DeepSeek V4 ProV4 Pro with reasoning + non-reasoning modes. Cache hit $0.003625. Replaces DeepSeek Reasoner R1.
DeepSeek V3DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tok
DeepSeek V3 0324DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/d
DeepSeek V3.1DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 ba
DeepSeek V3.1 TerminusDeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, inc