DeepSeek R1 is a dedicated reasoning model that thinks step-by-step before answering, excelling at math, logic, and multi-step problem solving. The 0528 update improves accuracy and reduces overthinking on simple prompts.
Drop-in OpenAI replacement. Change only the base_url and model.
# Python -pip install openai from openai import OpenAI client = OpenAI( base_url="https://meshtok.com/v1", api_key="sk-your-MeshTok-key", ) resp = client.chat.completions.create( model="deepseek/deepseek-r1-0528", messages=[{"role":"user","content":"Hello!"}], ) print(resp.choices[0].message.content)
# cURL curl https://meshtok.com/v1/chat/completions \ -H "Authorization: Bearer sk-your-MeshTok-key" \ -H "Content-Type: application/json" \ -d '{"model":"deepseek/deepseek-r1-0528","messages":[{"role":"user","content":"Hello!"}]}'
Other models you might consider.
DeepSeek’s flagship reasoning model.
Fast and ultra-cheap, for high-volume tasks.
Reliable general-purpose workhorse.
General-purpose chat model.