Summary
A second model is one call away, and you decide how long and how adventurous its answer is.
The tool takes a prompt rather than a message array, so it suits a self-contained question — a proof, a translation, a rewrite — more than a continuing conversation. temperature and max_tokens are the two levers, and they are per call, which makes it practical to ask the same question twice under different settings and compare.
What it is
A single-tool bridge to the DeepSeek R1 model. deepseek_r1 takes a prompt, a temperature and a max_tokens, and returns generated text.
What you get
- Text generated by DeepSeek R1 from a prompt you pass
- Per-call control of randomness through temperature and of length through max_tokens
Requirements
A DeepSeek account with an API key in DEEPSEEK_API_KEY, and Node on your PATH.