deepseek-r1

DeepSeek · DeepSeek R1

DeepSeek's reasoning model — an open-weight competitor to OpenAI's o-series. R1 uses extended chain-of-thought to achieve frontier-level reasoning at a fraction of the cost. Excellent for math, logic, and step-by-step problem solving.

pros

• frontier-level reasoning quality
• open weights
• exceptionally cheap for its capability
• strong math and logic

cons

• slow — extended thinking adds latency
• verbose (shows reasoning trace)
• weaker at creative writing

use this model on surp.ivc.lol

Reference this model in a custom combo to always get the cheapest price for it:

curl -X POST https://surp.ivc.lol/api/combos/custom \
  -H "Content-Type: application/json" \
  -d '{"name":"my combo","models":["deepseek-r1"]}'

Or compare it against alternatives: compare deepseek-r1 »